Search

Digital Pathology or whole slide imaging (WSI) is a diagnostic evaluation technique that produces digital images of high quality from tissue fragments. These images are formed on glass slides and evaluated by pathologist with the aid of microscope. As the concept of digital pathology is introduced, these high quality images are digitized and produced on-screen whole slide images in the form of digital files. This has paved the way for pathologists to collaborate with other pathology professionals in case of any additional recommendations and also provides remote working opportunities. The application of digital pathology in clinical practice is glazed with several advantages and adopted by pathologists and researchers for clinical, educational and research purposes. Moreover, digital pathology system integration requires an intensive effort from multiple stakeholders. All pathology departments have different needs, case usage, and blueprints, even though the framework elements and variables for effective clinical integration can be applied to any institution aiming for digital transformation. This article reviews the background and developmental phases of digital pathology and its application in clinical services, educational and research activities. [ABSTRACT FROM AUTHOR]

Visibility can be interpreted as the largest distance of an object that can be recognized or detected under a bright environment that can be used as an environmental indicator for weather conditions and air pollution. The accuracy of the classical approach of visibility calculation, in which meteorological laws and image feature extraction from digital images are used, depends on the quality and noise disturbances of the image. Therefore, artificial intelligence (AI) and digital image approaches have been proposed for visibility estimation in the past. Image features for the whole digital image are generated by pre-trained convolutional neural networks, and the Artificial Neural Network (ANN) is designed for correlation between image features and visibilities. Instead of using the information of the whole digital images, past research has been proposed to identify effective subregions from which image features are generated. A generalized regression neural network (GRNN) was designed to correlate the image features with the visibilities. Past research results showed that this method is more accurate than the classical approach of using handcrafted features. However, the selection of effective subregions of digital images is not fully automated and is based on manual selection by expert judgments. In this paper, we proposed an automatic effective subregion selection method using landmark object extraction techniques. Image features are generated from these LMO subregions, and the ANN is designed to approximate the mapping between LMO regions' feature values and visibility values. The experimental results show that this approach can minimize the reductant information for ANN training and improve the accuracy of visibility estimation as compared to the single image approach. [ABSTRACT FROM AUTHOR]

Traditional facial recognition is realized by facial recognition algorithms based on 2D or 3D digital images and has been well developed and has found wide applications in areas related to identification verification. In this work, we propose a novel live face detection (LFD) method by utilizing snapshot spectral imaging technology, which takes advantage of the distinctive reflected spectra from human faces. By employing a computational spectral reconstruction algorithm based on Tikhonov regularization, a rapid and precise spectral reconstruction with a fidelity of over 99% for the color checkers and various types of "face" samples has been achieved. The flat face areas were extracted exactly from the "face" images with Dlib face detection and Euclidean distance selection algorithms. A large quantity of spectra were rapidly reconstructed from the selected areas and compiled into an extensive database. The convolutional neural network model trained on this database demonstrates an excellent capability for predicting different types of "faces" with an accuracy exceeding 98%, and, according to a series of evaluations, the system's detection time consistently remained under one second, much faster than other spectral imaging LFD methods. Moreover, a pixel-level liveness detection test system is developed and a LFD experiment shows good agreement with theoretical results, which demonstrates the potential of our method to be applied in other recognition fields. The superior performance and compatibility of our method provide an alternative solution for accurate, highly integrated video LFD applications. [ABSTRACT FROM AUTHOR]

Cloud Computing (CC) is a fast emerging field that enables consumers to access network resources on-demand. However, ensuring a high level of security in CC environments remains a significant challenge. Traditional encryption algorithms are often inadequate in protecting confidential data, especially digital images, from complex cyberattacks. The increasing reliance on cloud storage and transmission of digital images has made it essential to develop strong security measures to stop unauthorized access and guarantee the integrity of sensitive information. This paper presents a novel Crayfish Optimization based Pixel Selection using Block Scrambling Based Encryption Approach (CFOPS-BSBEA) technique that offers a unique solution to improve security in cloud environments. By integrating steganography and encryption, the CFOPS-BSBEA technique provides a robust approach to secure digital images. Our key contribution lies in the development of a three-stage process that optimally selects pixels for steganography, encodes secret images using Block Scrambling Based Encryption, and embeds them in cover images. The CFOPS-BSBEA technique leverages the strengths of both steganography and encryption to provide a secure and effective approach to digital image protection. The Crayfish Optimization algorithm is used to select the most suitable pixels for steganography, ensuring that the secret image is embedded in a way that minimizes detection. The Block Scrambling Based Encryption algorithm is then used to encode the secret image, providing an additional layer of security. Experimental results show that the CFOPS-BSBEA technique outperforms existing models in terms of security performance. The proposed approach has significant implications for the secure storage and transmission of digital images in cloud environments, and its originality and novelty make it an attractive contribution to the field. Furthermore, the CFOPS-BSBEA technique has the potential to inspire further research in secure cloud computing environments, making the way for the development of more robust and efficient security measures. [ABSTRACT FROM AUTHOR]

Chip defect detection is a crucial aspect of the semiconductor production industry, given its significant impact on chip performance. This paper proposes a lightweight neural network with dual decoding paths for LED chip segmentation, named LDDP-Net. Within the LDDP-Net framework, the receptive field of the MobileNetv3 backbone is modified to mitigate information loss. In addition, dual decoding paths consisting of a coarse decoding path and a fine-grained decoding path in parallel are developed. Specifically, the former employs a straightforward upsampling approach, emphasizing macro information. The latter is more detail-oriented, using multiple pooling and convolution techniques to focus on fine-grained information after deconvolution. Moreover, the integration of intermediate-layer features into the upsampling operation enhances boundary segmentation. Experimental results demonstrate that LDDP-Net achieves an mIoU (mean Intersection over Union) of 90.29% on the chip dataset, with parameter numbers and FLOPs (Floating Point Operations) of 2.98 M and 2.24 G, respectively. Comparative analyses with advanced methods reveal varying degrees of improvement, affirming the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The modern society generates vast amounts of digital content, whose credibility plays a pivotal role in shaping public opinion and decision-making processes. The rapid development of social networks and generative technologies, such as deepfakes, significantly increases the risk of disinformation through image manipulation. This article aims to review methods for verifying images' integrity, particularly through deep learning techniques, addressing both passive and active approaches. Their effectiveness in various scenarios has been analyzed, highlighting their advantages and limitations. This study reviews the scientific literature and research findings, focusing on techniques that detect image manipulations and localize areas of tampering, utilizing both statistical properties of images and embedded hidden watermarks. Passive methods, based on analyzing the image itself, are versatile and can be applied across a broad range of cases; however, their effectiveness depends on the complexity of the modifications and the characteristics of the image. Active methods, which involve embedding additional information into the image, offer precise detection and localization of changes but require complete control over creating and distributing visual materials. Both approaches have their applications depending on the context and available resources. In the future, a key challenge remains the development of methods resistant to advanced manipulations generated by diffusion models and further leveraging innovations in deep learning to protect the integrity of visual content. [ABSTRACT FROM AUTHOR]

In recent years, the internet has developed rapidly. With the popularity of social media, uploading and backing up digital images has become the norm. A huge number of digital images are circulating on the internet daily, and issues related to information security follow. To protect intellectual property rights, digital watermarking is an indispensable technology. However, the common lossy compression technology in the network transmission process is a big problem for watermarking. This paper describes an innovative semi-blind watermarking method with the use of deep convolutional generative adversarial networks (DCGANs) for hiding and extracting watermarks from JPEG-compressed images. The proposed method achieves an average peak signal-to-noise ratio (PSNR) of 49.99 dB, a structural similarity index (SSIM) of 0.95, and a bit error rate (BER) of 0.008 across varying JPEG quality factors. The process is based on an embedder, decoder, generator, and discriminator. It allows watermarking, decoding, or reconstruction to be symmetric such that there is less distortion and durability is improved. It constructs a specific generator for each image and watermark that is supposed to be protected. Experimental results show that, with the variety of JPEG quality factors, the restored watermark achieves a remarkably low corrupted rate, outstripping recent deep learning-based watermarking methods. [ABSTRACT FROM AUTHOR]

Background/Objectives: The damage assessment of dental instruments, such as endodontic files, is crucial to ensure patient safety and treatment quality. Conventional scanning electron microscopy (SEM) has been the gold standard for this purpose; however, its limited accessibility and complex sample preparation protocols hinder its routine use in clinical settings. This study proposes a novel system that leverages digital photography and advanced image processing techniques as a viable alternative to SEM. Methods: Our system accurately detects early instrument damage by capitalizing on the high resolution of digital images. Its exceptionally user-friendly interface, portability, and key features make it highly suitable for daily clinical practice. Results: Our findings suggest that the proposed system provides image quality comparable to SEM. Conclusions: Image stacking provides a practical, efficient, and objective method for assessing endodontic instruments' morphology. By detecting early damage, this system significantly improves the safety and quality of endodontic procedures, especially for reusable NiTi files, instilling confidence and security in its use. It offers a cost-effective and user-friendly alternative to traditional methods such as visual inspection and SEM, making it a comfortable and confident choice for both research and clinical settings. [ABSTRACT FROM AUTHOR]

Road damage often includes potholes, cracks, lane degradation, and surface shading. Potholes are a common problem in pavements. Detecting them is crucial for maintaining infrastructure and ensuring public safety. A thorough assessment of pavement conditions is required before planning any preventive repairs. Herein, we report the use of transfer learning and deep learning (DL) models to preprocess digital images of pavements for better pothole detection. Fourteen models were evaluated, including MobileNet, MobileNetV2, NASNetMobile, DenseNet121, DenseNet169, InceptionV3, DenseNet201, ResNet152V2, EfficientNetB0, InceptionResNetV2, Xception, and EfficientNetV2M. The study introduces a modified MobileNetV2 (MMNV2) model designed for fast and efficient feature extraction. The MMNV2 model exhibits improved classification, detection, and prediction accuracy by adding a five-layer pre-trained network to the MobileNetV2 framework. It combines deep learning, deep neural networks (DNN), and transfer learning, which resulted in better performance compared to other models. The MMNV2 model was tested using a dataset of 5,000 pavement images. A learning rate of 0.001 was used to optimize the model. It classified images into 'normal' or 'pothole' categories with 99.95% accuracy. The model also achieved 100% recall, 99.90% precision, 99.95% F1-score, and a 0.05% error rate. The MMNV2 model uses fewer parameters while delivering better results. It offers a promising solution for real-world applications in pothole detection and pavement assessment. [ABSTRACT FROM AUTHOR]

The dynamic identification of the deformation of a noise barrier column is of great significance to the monitoring of its health. At the same time, the maximum stress of the column is an important indicator for the evaluation of its health status. Traditional contact displacement monitoring installs sensors on the structure, requires a lot of wiring and data acquisition equipment, and establishes a relatively independent and stable displacement reference system. Affected by the environment, wear, and material aging, the efficiency and reliability of data acquisition are reduced. A monitoring method based on digital image has the advantages of non-contact monitoring, high precision, and strong reliability. The existing DIC detection methods are limited by processor performance and image resolution, which are difficult to apply to engineering detection. In this paper, a structural displacement identification method based on convolutional neural networks (CNNs) and DIC technology is proposed. In this method, the data set is formed according to the column displacement cloud image obtained by DIC analysis, and the data set is enhanced by data normalization and region division. Through the analysis of the number of network layers and learning rate, the model design of the deep learning network is carried out. The high-speed camera image results of the test are introduced and identified by the static loading test of the equal-scale sound barrier. The results show that the structural displacement identification method based on CNN and DIC technology can accurately identify the displacement change in the structure, which greatly improves the efficiency of image displacement calculation using DIC technology. [ABSTRACT FROM AUTHOR]

Understanding rock hardness on extraterrestrial planets offers valuable insights into planetary geological evolution. Rock hardness correlates with morphological parameters, which can be extracted from navigation images, bypassing the time and cost of rock sampling and return. This research proposes a machine-learning approach to predict extraterrestrial rock hardness using morphological features. A custom dataset of 1496 rock images, including granite, limestone, basalt, and sandstone, was created. Ten features, such as roundness, elongation, convexity, and Lab color values, were extracted for prediction. A foundational model combining Random Forest (RF) and Support Vector Regression (SVR) was trained through cross-validation. The output of this model was used as the input for a meta-model, undergoing linear fitting to predict Mohs hardness, forming the Meta-Random Forest and Support Vector Regression (MRFSVR) model. The model achieved an R2 of 0.8219, an MSE of 0.2514, and a mean absolute error of 0.2431 during validation. Meteorite samples were used to validate the MRFSVR model's predictions. The model is used to predict the hardness distribution of extraterrestrial rocks using images from the Tianwen-1 Mars Rover Navigation and Terrain Camera (NaTeCam) and a simulated lunar rock dataset from an open-source website. The results demonstrate the method's potential for enhancing extraterrestrial exploration. [ABSTRACT FROM AUTHOR]

Digital image source identification primarily focuses on analyzing and detecting the machine imprints or camera fingerprints left by imaging devices during the imaging process to trace the origin of digital images. The development of a swift search algorithm is crucial for the effective implementation of camera source identification. Despite its importance, this domain has witnessed limited research, with existing studies predominantly focusing on search efficiency while neglecting robustness, which is essential. In practical scenarios, query images often suffer from poor signal quality due to noise, and the variability in fingerprint quality across different sources presents a significant challenge. Conventional brute-force search algorithms (BFSAs) prove largely ineffective under these conditions because they lack the necessary robustness. This paper addresses the issues in digital image source identification by proposing a rapid fingerprint search algorithm based on global information. The algorithm innovatively introduces a search priority queue (SPQ), which analyzes the global correlation between the query fingerprint and all reference fingerprints in the database to construct a comprehensive priority ranking, thereby achieving the efficient retrieval of matching fingerprints. Compared to the traditional brute-force search algorithm (BFSA), our method significantly reduces computational complexity in large-scale databases, optimizing from O (n N) to O (n log N) , where n is the length of the fingerprint, and N is the number of fingerprints in the database. Additionally, the algorithm demonstrates strong robustness to noise, maintaining a high matching accuracy rate even when image quality is poor and noise interference is significant. Experimental results show that in a database containing fingerprints from 70 cameras, our algorithm is 50% faster in average search time than BFSA, and its matching accuracy rate exceeds 90% under various noise levels. This method not only improves the efficiency and accuracy of digital image source identification but also provides strong technical support for handling large-scale image data, with broad application prospects in fields such as copyright protection and forensic evidence. [ABSTRACT FROM AUTHOR]

In the era of widespread digital image sharing on social media platforms, deep-learning-based watermarking has shown great potential in copyright protection. To address the fundamental trade-off between the visual quality of the watermarked image and the robustness of watermark extraction, we explore the role of structural features and propose a novel edge-aware watermarking framework. Our primary innovation lies in the edge-aware secret hiding module (EASHM), which achieves adaptive watermark embedding by aligning watermarks with image structural features. To realize this, the EASHM leverages knowledge distillation from an edge detection teacher and employs a dual-task encoder that simultaneously performs edge detection and watermark embedding through maximal parameter sharing. The framework is further equipped with a social network noise simulator (SNNS) and a secret recovery module (SRM) to enhance robustness against common image noise attacks. Extensive experiments on three public datasets demonstrate that our framework achieves superior watermark imperceptibility, with PSNR and SSIM values exceeding 40.82 dB and 0.9867, respectively, while maintaining an over 99% decoding accuracy under various noise attacks, outperforming existing methods by significant margins. [ABSTRACT FROM AUTHOR]

Digital pathology using whole-slide imaging (WSI) scanners aids pathologists challenged by diagnostic volume and novel diagnostic methods. Colour reproducibility of WSI scanners is crucial for accurate digital diagnoses. We propose an objective and quantitative method for evaluating colour reproduction in digital images of pathological specimens from two perspectives: true colour value reproduction and colour discrimination. We define 57 critical features for evaluation, extract tissue structures, and establish diagnostic criteria. Our method is unique and useful for clinical use. We tested a prototype scanner, and it satisfied all criteria for true colour value reproduction (all the colour samples corresponding to the selected tissue evaluation points were experimentally within the acceptable range) and colour discrimination (the colour difference ΔE2000 calculated from the corresponding colour sample combinations exceeded the lower permissible limit for the selected discrimination points). This evaluation method and WSI scanner can contribute to accurate colour reproduction in digital pathology. [ABSTRACT FROM AUTHOR]

Background and Objectives: The present study aims to assess and compare the accuracy of post-space impressions captured by three different intraoral scanners (IOS) using various canal diameters. Methods: Three extracted natural maxillary central incisors were selected and prepared for a 1 mm wide margin and a 3 mm ferrule. All steps required for the endodontic procedure were performed, and the post space was prepared using post drills. The post length was kept constant at 12 mm, whereas the width was varied (Group 1: 1.4 mm, Group 2: 1.6 mm, and Group 3: 1.8 mm). Three IOSs (Trios3, iTero2, and Medit i700) were used to acquire a digital impression of the prepared post space. Each tooth was scanned 10 times by each scanner. So, in the end, 90 digital images were recorded, and the STL files were stored. GC Pattern resin was used to fabricate resin post and core patterns, which were scanned using an extraoral scanner (EOS). The STL file obtained was used as the reference file. To evaluate the trueness of the tested IOSs, each three-dimensional scan from an IOS was superimposed on the reference scan with the help of the Medit Design software 2.1.4. The software generates color plots and gives numerical values as deviations in the Root mean square (RMS) for the variance between the two superimposed scans. The data collected was tabulated for statistical analysis. One Way ANOVA was used to test the significance difference between three different IOSs, followed by Bonferroni Post-hoc test pairwise test to identify the differences between every two different IOS. Statistical significance was set at p < 0.05. Results: The mean deviation for trueness in post space impression values recorded by the Medit i700 was highest among groups 1, 2, and 3 [0.825 (±0.071), 0.673 (±0.042) and 0.516 (±0.039), respectively], followed by iTero2 [0.738 (±0.081), 0.569 (±0.043) and 0.470 (±0.037), respectively] and Trios3 [0.714 (±0.062), 0.530 (±0.040) and 0.418 (±0.024), respectively]. Significant differences were found between the groups for all three IOSs (Trios3: p-value < 0.0001; iTero2: p-value < 0.0001; Medit i700: p-value < 0.0001). Conclusions: Within the limitations of this study, it can be concluded that Trios3 IOS has higher accuracy (as it exhibited minimal deviation for trueness) in recording post space, followed by iTero2 and Mediti700 IOS. As the diameter of the post space is increased, the accuracy of recording by IOS increases. For all the tested IOSs (except for Trios3 and iTero2, when used to record post space with 1.8 mm canal diameter), the deviations in trueness were higher than the clinically acceptable limits. Thus, IOSs should be used cautiously when recording impressions of post spaces. [ABSTRACT FROM AUTHOR]

Chaos-based encryption is promising for safeguarding digital images. Nonetheless, existing chaos-based encryption algorithms still exhibit certain shortcomings. Given this, we propose a novel multi-channel image encryption algorithm that leverages pixel reorganization and hyperchaotic maps (MIEA-PRHM). Our MIEA-PRHM algorithm employs two hyperchaotic maps to jointly generate chaotic sequences, ensuring a larger key space and better randomness. During the encryption process, we first convert input images into two fused matrices through pixel reorganization. Then, we apply two rounds of scrambling and diffusion operations, coupled with one round of substitution operations, to the high 4-bit matrix. For the low 4-bit matrix, we conduct one round of substitution and diffusion operations. Extensive experiments and comparisons demonstrate that MIEA-PRHM outperforms many recent encryption algorithms in various aspects, especially in encryption efficiency. [ABSTRACT FROM AUTHOR]

Physical unclonable function labels have emerged as a promising candidate for achieving unbreakable anticounterfeiting. Despite their significant progress, two challenges for developing practical physical unclonable function systems remain, namely 1) fairly few high-dimensional encoded labels with excellent material properties, and 2) existing authentication methods with poor noise tolerance or inapplicability to unseen labels. Herein, we employ the linear polarization modulation of randomly distributed fluorescent nanodiamonds to demonstrate, for the first time, three-dimensional encoding for diamond-based labels. Briefly, our three-dimensional encoding scheme provides digitized images with an encoding capacity of 109771 and high distinguishability under a short readout time of 7.5 s. The high photostability and inertness of fluorescent nanodiamonds endow our labels with high reproducibility and long-term stability. To address the second challenge, we employ a deep metric learning algorithm to develop an authentication methodology that computes the similarity of deep features of digitized images, exhibiting a better noise tolerance than the classical point-by-point comparison method. Meanwhile, it overcomes the key limitation of existing artificial intelligence-driven classification-based methods, i.e., inapplicability to unseen labels. Considering the high performance of both fluorescent nanodiamonds labels and deep metric learning authentication, our work provides the basis for developing practical physical unclonable function anticounterfeiting systems. The authors use polarized fluorescent nanodiamonds to achieve high-dimensional encoding for physical unclonable functions, and propose a deep metric learning based approach for robust authentication of unseen labels. [ABSTRACT FROM AUTHOR]

In this world of digitization, most of the data is in the form of images acquired using camera. Image enhancement plays a vital role in the quality improvement of digital images. In this work, a combined approach based on the contrast limited adaptive histogram equalization (CLAHE) and Retinex algorithm is proposed. It is a wavelet based Retinex algorithm with adaptive histogram equalization and gaussian filter. Firstly, the image is enhanced using CLAHE. Then the image is decomposed using Daubechies wavelet followed by the Retinex algorithm, which uses low frequency components to enhance the image. Lastly, a gaussian filter is used to smoothen the image. The dataset of maize leaf disease is used for the analysis of quality enhancement and denoising. It is clear from the results that the proposed method improves the quality by reducing the noise of the maize leaf images. Theses refined images can be used for maize leaves disease detection and classification system to achieve high accuracy. [ABSTRACT FROM AUTHOR]

The extraction of device-independent color values from affordable and accessible digital images based on a standard color space system is crucially necessary for agricultural applications, where color information for plant monitoring or diagnostics is required. This study aimed to develop a transformation matrix for obtaining XYZ color coordinates from the RGB values of digital images for agricultural applications. The calibration procedure was based on Munsell and Macbeth color charts. The color coordinates of eight color charts were measured, and the transformation matrices were built. Leaf samples of six different plants were used and compared based on the proposed transformation technique. The actual XYZ values of plant leaves were measured, and the RGB values were derived from the digital images. The results indicate that the Macbeth color chart with 24 colors had the best performance, with an average ∆ELAB and CIEDE2000 of less than 1.77 and 1.97, respectively. The findings demonstrate that the proposed transformation matrix was successful in converting RGB values to XYZ values and can be employed as a quick, easy, and inexpensive technique for obtaining standard color information. [ABSTRACT FROM AUTHOR]

Lately, image encryption has stand out as a highly urgent demand to provide high security for digital images against use and unauthorized distribution. A lot of existing researches use chaotic systems, symmetric or asymmetric schemes for image encryption, but cryptosystem based on one encryption technique only, faces many challenges like weak security and low complexity. Therefore, incorporating two or more different ciphering methods yields a secure and efficient algorithm to protect image information. In this work, a new image cryptosystem is suggested by joining zigzag scan technique, RSA algorithm and chaotic systems. These three security factors introduce Triple Incorporated Ciphering stages system (TIC). Initially, the plaintext image is divided into 8 × 8 non-overlapping blocks, then the odd blocks are isolated from the even blocks. After that, a new modified zigzag scan in two different directions is adopted for shuffling pixels in the odd and even blocks. This operation effectively enhances the shuffling degree. Next, the RSA algorithm is utilized after combining the scrambled blocks in one matrix. Finally, chaotic systems are implemented on the resultant encrypted matrix to complete the ciphering process. The chaos is implemented in two steps; confusion and diffusion. Duffing map is exploited in the confusion stage, whereas Lu system is adopted on the shuffled matrix in the ¨ diffusion stage. The simulation results show the superiority of TIC in both security and attacks robustness compared to other cryptographic algorithms. Therefore, TIC can be exploited in real-time communication systems for secure image transmission. [ABSTRACT FROM AUTHOR]

The article delves into the complex relationship between copyright law and AI-generated imagery, emphasizing the role of human authorship in creating original works. It discusses the necessity for artists to make significant editorial changes to AI-generated images to qualify for copyright protection, citing legal precedents like Burrow-Giles v. Sarony and Feist Publications v. Rural Telephone Service Co. The text underscores the importance of an artist's intellectual contributions and enhancements in determining authorship over AI-generated images, advocating for clear guidelines to assess human authorship in Generative Artificial Intelligence (GenAI) imagery. By proposing the implementation of the Assessment as a tool for evaluating human authorship in GenAI imagery, the article suggests that standardized criteria could enhance consistency, transparency, and encourage investment in GenAI technology, leading to economic growth and innovation. [Extracted from the article]

Copyright of Lilloa is the property of Fundacion Miguel Lillo and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The development of new technologies has made image watermarking crucial in the digital era to preserve and protect illegal distribution of images against unauthorized users. This paper presents a robust image watermarking technique that employs a set of embedding rules in the three-level of integer wavelet transform (IWT). The proposed method aims to achieve high robustness of image watermarking while maintaining the imperceptibility. The proposed scheme divides the red and green layers into non-overlapping 16×16 blocks. Three levels of IWT are applied to obtain 2×2 LL sub-band, four coefficients of IWT are then modified based on the proposed set of rules for embedding watermark. The experimental results demonstrate a comparison of the proposed embedding and the existing methods. The proposed scheme produced an average NC value of 0.965 against the median filter. The results also showed the imperceptibility of the the image with a PSNR of 45.1760 db and SSIM of 0.9995. [ABSTRACT FROM AUTHOR]

Soil roughness, defined as the irregularities of the soil surface, yields significant information about soil water storage, infiltration and overland flow and, thus, is a key factor in characterizing the quality of the terrain; it is often used as input in many synthetic general agricultural models and in particular in soil moisture estimation models. In this paper, we propose a framework that combines a specific setup for data acquisition with deep convolutional networks for actual estimation. The former relies on projecting a line red laser beam on the analysed soil surface followed by digital color image acquisition. The later, involves two convolutional models that are trained in a supervised manner to predict the soil roughness. The data set was produced in the laboratory both on synthetic and real soil samples. The labels used in the training process are the soil roughness values measured by using a pinboard. The detailed evaluation showed that the error of the automatic precision lies in the range of ground truth deviation, thus validating the proposed procedure. [ABSTRACT FROM AUTHOR]

The article presents the results of adapting the digital image correlation method for the possibility of diagnosing reinforced concrete structures. Reinforced concrete (RC) bending elements are the most widely used in construction practice, which determines the importance of reliable estimation of their stress-strain state. The purpose of this study includes reliable theoretical and experimental investigation of the strength and deformability parameters of the RC beam. The experimental study was conducted using digital image correlation and sub-micron contactless gauges. Experimental data was verified with the calculation of the stress-strain state of the RC beam according to DBN V.2.6-98:2009 and Eurocode 2 and the finite-element modelling (FEM). As a result, the values of deflections, concrete and rebar strains were obtained and presented as corresponding diagrams. The results of all the methods are within the same ranges. Also, the form and character of corresponding diagrams are very similar. The indicated deviations were within acceptable limits. It was noted that the theoretical calculation generally provides lower strain values, which is a satisfactory result, as it indicates the bearing capacity reserves provided by the current regulations. The propagation of cracks was monitored during the experiment and the measured cracks opening was compared with theoretical assumptions. Theoretical values are higher than experimental, which shows certain conservativity of valid normative regulations. The experimental and theoretical results were in good correspondence, which confirms their reliability. It was concluded, that the proposed in the study complex theoretic-experimental approach provides essential information about the strength and deformability of the structure. [ABSTRACT FROM AUTHOR]

Beyond the realm of soft topology, soft continuity can aid in the creation of digital images and computational topological applications. This paper investigates soft almost weakly continuous, a novel family of generalized soft continuous functions. The soft pre-continuous and soft weakly continuous function classes are included in this class. We obtain many characterizations of soft almost weakly continuous functions. Furthermore, we investigate the link between soft almost weakly continuous functions and their general topology counterparts. We present adequate conditions for a soft almost weakly continuous function to become soft weakly continuous (soft pre-continuous). We also present various results of soft composition, restriction, preservation, product, and soft graph theorems in terms of soft almost weakly continuous functions. [ABSTRACT FROM AUTHOR]

Introduction: Diagnosing oral cancer is crucial in healthcare, with technological advancements enhancing early detection and outcomes. This review examines the impact of handheld AI-based tools, focusing on Convolutional Neural Networks (CNNs) and their advanced architectures in oral cancer diagnosis. Methods: A comprehensive search across PubMed, Scopus, Google Scholar, and Web of Science identified papers on deep learning (DL) in oral cancer diagnosis using digital images. The review, registered with PROSPERO, employed PRISMA and QUADAS-2 for search and risk assessment, with data analyzed through bubble and bar charts. Results: Twenty-five papers were reviewed, highlighting classification, segmentation, and object detection as key areas. Despite challenges like limited annotated datasets and data imbalance, models such as DenseNet121, VGG19, and EfficientNet-B0 excelled in binary classification, while EfficientNet-B4, Inception-V4, and Faster R-CNN were effective for multiclass classification and object detection. Models achieved up to 100% precision, 99% specificity, and 97.5% accuracy, showcasing AI's potential to improve diagnostic accuracy. Combining datasets and leveraging transfer learning enhances detection, particularly in resource-limited settings. Conclusion: Handheld AI tools are transforming oral cancer diagnosis, with ethical considerations guiding their integration into healthcare systems. DL offers explainability, builds trust in AI-driven diagnoses, and facilitates telemedicine integration. [ABSTRACT FROM AUTHOR]

The computer network has fundamentally transformed modern interactions, enabling the effortless transmission of multimedia data. However, the openness of these networks necessitates heightened attention to the security and confidentiality of multimedia content. Digital images, being a crucial component of multimedia communications, require robust protection measures, as their security has become a global concern. Traditional color image encryption/decryption algorithms, such as DES, IDEA, and AES, are unsuitable for image encryption due to the diverse storage formats of images, highlighting the urgent need for innovative encryption techniques. Chaos-based cryptosystems have emerged as a prominent research focus due to their properties of randomness, high sensitivity to initial conditions, and unpredictability. These algorithms typically operate in two phases: shuffling and replacement. During the shuffling phase, the positions of the pixels are altered using chaotic sequences or matrix transformations, which are simple to implement and enhance encryption. However, since only the pixel positions are modified and not the pixel values, the encrypted image's histogram remains identical to the original, making it vulnerable to statistical attacks. In the replacement phase, chaotic sequences alter the pixel values. This research introduces a novel encryption technique for color images (RGB type) based on DNA subsequence operations to secure these images, which often contain critical information, from potential cyber-attacks. The suggested method includes two main components: a high-speed permutation process and adaptive diffusion. When implemented in the MATLAB software environment, the approach yielded promising results, such as NPCR values exceeding 98.9% and UACI values at around 32.9%, demonstrating its effectiveness in key cryptographic parameters. Security analyses, including histograms and Chi-square tests, were initially conducted, with passing Chi-square test outcomes for all channels; the correlation coefficient between adjacent pixels was also calculated. Additionally, entropy values were computed, achieving a minimum entropy of 7.0, indicating a high level of randomness. The method was tested on specific images, such as all-black and all-white images, and evaluated for resistance to noise and occlusion attacks. Finally, a comparison of the proposed algorithm's NPCR and UAC values with those of existing methods demonstrated its superior performance and suitability. [ABSTRACT FROM AUTHOR]

In Oaxaca, Mexico, there are more than 30 species of the Agave genus, and its cultivation is of great economic and social importance. The incidence of pests, diseases, and environmental stress cause significant losses to the crop. The identification of damage through non-invasive tools based on visual information is important for reducing economic losses. The objective of this study was to evaluate and compare five deep learning models: YOLO versions 7, 7-tiny, and 8, and two from the Detectron2 library, Faster-RCNN and RetinaNet, for the detection and classification of Agave angustifolia plants in digital images. In the town of Santiago Matatlán, Oaxaca, 333 images were taken in an open-air plantation, and 1317 plants were labeled into five classes: sick, yellow, healthy, small, and spotted. Models were trained with a 70% random partition, validated with 10%, and tested with the remaining 20%. The results obtained from the models indicate that YOLOv7 is the best-performing model, in terms of the test set, with a mAP of 0.616, outperforming YOLOv7-tiny and YOLOv8, both with a mAP of 0.606 on the same set; demonstrating that artificial intelligence for the detection and classification of Agave angustifolia plants under planting conditions is feasible using digital images. [ABSTRACT FROM AUTHOR]

The huge advance of digital communication and networks has led to enormous storage and transmission of information over public networks. Nevertheless, the assurance of information security remains incomplete across these unsecured networks. Currently, digital images are the primary mean for sharing information over open networks. Consequently, the confidentiality of digital images during storage and transmission has become a crucial concern, particularly when sharing sensitive information. Image encryption has emerged as a solution to this problem. This paper presents an image encryption technique based on multiple one-dimensional chaotic maps and DNA coding. The technique employs three one-dimensional chaotic maps, including the logistic map, tent map and piecewise map, multiple times to produce 18 random sequences with different initial values and parameters. SHA-512 hash function is used to indicate the initial values of chaotic maps. For encrypting images, the binary elements from various sequences of chaotic maps are amalgamating to alter the pixel intensities of the image in the diffusion process. Dynamic DNA coding is performed through random selection of DNA rules and operations (XOR, XNOR and Addition) to each pixel in the image. The technique is enforced using circular rotations which are applied randomly to each key. The proposed technique is evaluated using many standard images. Different performance metrics have been measured. The empirical findings illustrate the security and resilience of the suggested method and its ability to resist statistical and differential attacks. [ABSTRACT FROM AUTHOR]

The portability and popularity of smartphones makes it easy to capture digital images in a variety of situations, including witnessing criminal activity. Forensic analysis of digital images captured by smartphone-cameras could be used for legal and investigative purposes, not only to have a recording of an act, but also to establish a relationship between a digital image and its capture device, and between the latter and a person. Fortunately, given the similarities, forensic ballistics techniques and procedures used to identify weapons from fired bullets can be used to identify smartphone-cameras from digital images. However, while there are several solutions for identifying smartphone-cameras from digital images, not all of them focus on two key issues: reducing the number of reference images used to create the fingerprint of the smartphone-camera and reducing the processing time for identification. To address these issues, a method based on a two-degree-of-freedom discriminant analysis using pixel intensity and intrinsic noise in digital images is proposed. It uses a Mahalanobis classifier to compare the traces left by the capture source in a digital image with the fingerprints calculated for the candidate smartphone-cameras. This allows the identification of the most likely smartphone-camera that captured a digital image. A significant advantage of the proposed method is that it relies on a smaller number of reference images to estimate the smartphone-camera fingerprints. They are built using only fifteen reference images, as opposed to thirty or more images required by other techniques. This means faster processing times as image clippings are analyzed rather than whole digital images. The proposed method demonstrates high performance, since for disputed flat images it achieves an identification effectiveness rate of 87.50% with one reference image, and 100.00% when fifteen reference images are considered. For disputed natural images, it achieves an identification effectiveness rate of 97.50% with fifteen reference images. [ABSTRACT FROM AUTHOR]

Non-fungible tokens (NFTs), which are immutable and transferable tokens on blockchain networks, have been used to certify the ownership of digital images often grouped in collections. Depending on individual interests, wallets explore and purchase NFTs in one or more image collections. Among many potential factors of shaping purchase trajectories, this paper specifically examines how visual similarities between collections affect wallets' explorations. Our model characterizes each wallet's explorations with a Lévy flight and shows that wallets tend to favor collections having similar visual features to their previous purchases while their behaviors vary widely. The model also predicts the extent to which the next collection is close to the most recent collection of purchases with respect to visual features. These results are expected to enhance and support recommendation systems for the NFT market. [ABSTRACT FROM AUTHOR]

This research work presents a novel secured spatial steganography algorithm consisting of three stages. In the first stage, a secret message is divided into three parts, each is encrypted using a tan logistic map encryption key with a unique seed value. In the second stage, the encrypted parts are transformed into quick response codes, serving as a layer of channel coding. Subsequently, the quick response codes are decoded back into bit‐streams. To enhance security, a uniquely‐seeded Mersenne Twister key is generated and employed to apply DNA coding onto each bit‐stream. The resulting bit‐streams are then embedded in the least significant bits of the RGB channels of a cover image. Finally, the RGB channels are merged to form a single stego image. A comprehensive set of experimental analyses is conducted to evaluate the performance of the proposed secure steganography algorithm. The experimental results demonstrate the algorithm's robustness against various attacks and its ability to achieve high embedding capacity while maintaining imperceptibility. The proposed algorithm offers a promising solution for secure information hiding in the spatial domain, with potential applications in areas such as data transmission, digital forensics, and covert communication. [ABSTRACT FROM AUTHOR]

Image hiding is a task that embeds secret images in digital images without being detected. The performance of image hiding has been greatly improved by using the invertible neural network. However, current image hiding methods are less robust in the face of Joint Photographic Experts Group (JPEG) compression. The secret image cannot be extracted from the stego image after JPEG compression of the stego image. Some methods show good robustness for some certain JPEG compression quality factors but poor robustness for other common JPEG compression quality factors. An image‐hiding network (RIHINNet) that is robust to all common JPEG compression quality factors is proposed. First of all, the loss function is redesigned; thus, the secret image is hidden as much as possible in the area that is less likely to be changed after JPEG compression. Second, the classifier is designed, which can help the model to select the extractor according to the range of JPEG compression degree. Finally, the interval robustness of the secret image extraction is improved through the design of a denoising module. Experimental results show that this RIHINNet outperforms other state‐of‐the‐art image‐hiding methods in the face of JPEG compressed noise with random compression quality factors, with more than 10 dB peak signal‐to‐noise ratio improvement in secret image recovery on ImageNet, COCO and DIV2K datasets. [ABSTRACT FROM AUTHOR]

Traditional English corpora mainly collect information from a single modality, but lack information from multimodal information, resulting in low quality of corpus information and certain problems with recognition accuracy. To solve the above problems, this paper proposes to introduce depth information into multimodal corpora, and studies the construction method of English multimodal corpora that integrates electronic images and depth information, as well as the speech recognition method of the corpus. The multimodal fusion strategy adopted integrates speech signals and image information, including key visual information such as the speaker's lip movements and facial expressions, and uses deep learning technology to mine acoustic and visual features. The acoustic model in the Kaldi toolkit is used for experimental research.Through experimental research, the following conclusions were drawn: Under 15-dimensional lip features, the accuracy of corpus A under monophone model was 2.4% higher than that of corpus B under monophone model when the SNR (signal-to-noise ratio) was 10dB, and the accuracy of corpus A under the triphone model at the signal-to-noise ratio of 10dB was 1.7% higher than that of corpus B under the triphone model at the signal-to-noise ratio of 10dB. Under the 32-dimensional lip features, the speech recognition effect of corpus A under the monophone model at the SNR of 10dB was 1.4% higher than that of corpus B under the monophone model at the SNR of 10dB, and the accuracy of corpus A under the triphone model at the SNR of 10dB was 2.6% higher than that of corpus B under the triphone model at the SNR of 10dB. The English multimodal corpus with image and depth information has a high accuracy, and the depth information helps to improve the accuracy of the corpus. [ABSTRACT FROM AUTHOR]

This study proposes a novel forgery detection method based on the analysis of frequency components of images using the Discrete Fourier Transform (DFT). In recent years, face manipulation technologies, particularly Generative Adversarial Networks (GANs), have advanced to such an extent that their misuse, such as creating deepfakes indistinguishable to human observers, has become a significant societal concern. We reviewed two GAN architectures, StyleGAN and StyleGAN2, generating synthetic faces that were compared with real faces from the FFHQ and CelebA-HQ datasets. The key results demonstrate classification accuracies above 99%, with F1 scores of 99.94% for Support Vector Machines and 97.21% for Random Forest classifiers. These findings underline the fact that performing frequency analysis presents a superior approach to deepfake detection compared to traditional spatial detection methods. It provides insight into subtle manipulation cues in digital images and offers a scalable way to enhance security protocols amid rising digital impersonation threats. [ABSTRACT FROM AUTHOR]

Recently, it has become difficult to recognize and easier to misuse digital images due to the large number of editing tools available. Detecting forgeries in images is crucial for security and forensic purposes. Therefore, this research implements a deep learning (DL) method of convolutional autoencoder (CAE) which improves colorization-based image forgery detection by leveraging spatial and color information, increasing the detection accuracy. At first, the pre-processed input forgery images are used with the wiener filtering-contrast restricted improved histogram equalization (WE-CLAHE) technique. Hybrid dual-tree complex wavelet trigonometric transform (H-DTCWT) and VGG-16 are used to extract effective features from the clustered data. Improved horse herd optimization (IHH) is employed to reduce the dimensionality of a feature. At last, the CAE model is implemented to significantly recognize the image forgery. The accuracy of CASIA V1 and GRIP datasets of 99.95% and 99.97%, respectively is achieved. Hence, this implemented method obtains a high forgery detection performance than the existing methods. [ABSTRACT FROM AUTHOR]

Copyright of China Rural Water & Hydropower is the property of China Rural Water & Hydropower Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this paper, we propose a digital image encryption scheme based on Tabu Search (TS) algorithm and Chen's hyperchaos system. First, in order to enhance the security of the algorithm and resist the known-plaintext attack, the key is associated with the ordinary image, and the hash value generated by the ordinary image is used as the initial value of the hyperchaotic system. Moreover, the TS algorithm is used to obtain the optimal subsequence to scramble the sub-block image, which ensures the scrambling effect of the algorithm. In addition, for the sake of minimizing the correlation of neighborhood pixels and strengthening the effect of scrambling, the ordinary image is divided into blocks for scrambling and diffusion. Through simulation and experiments, the key sensitivity, differential attack and pure ciphertext attack are analyzed. Compared with the other encryption schemes, the results verify the effectiveness and reliability of the proposed scheme. [ABSTRACT FROM AUTHOR]

Blurriness is troublesome in digital images when captured under different illumination imaging conditions. To obtain an accurate blurred image quality assessment (IQA), a machine learning-based objective evaluation method for image sharpness under different illumination imaging conditions is proposed. In this method, the visual saliency, color difference, and gradient information are selected as the image features, and the relevant feature information of these three aspects is extracted from the image as the feature value for the blurred image evaluation under different illumination imaging conditions. Then, a particle swarm optimization-based general regression neural network (PSO-GRNN) is established to train the above extracted feature values, and the final blurred image evaluation result is determined. The proposed method was validated based on three databases, i.e., BID, CID2013, and CLIVE, which contain real blurred images under different illumination imaging conditions. The experimental results showed that the proposed method has good performance in evaluating the quality of images under different imaging conditions. [ABSTRACT FROM AUTHOR]

Potteries, one of the tools widely used by early humans, encapsulates rich historical information. Deep neural networks have been applied to analyzing pottery digital images, bypassing the need for intricate handcrafted features. However, existing models focus solely on pottery shape comparison, neglecting the analysis of their evolution across different historical periods. In this work, we propose a method based on deep learning to assist experts in identifying the evolutionary patterns of a given pottery type within their specified chronological divisions. First we train a convolutional neural network for pottery classification, extracting low and high level features that represent different ages of pottery samples. Next, we employ clustering algorithms to identify representative potteries for each historical period based on high level features. To facilitate intuitive comparisons across different ages, we use shallow features and compute cosine similarities between potteries, visualizing shape and decoration differences. This approach enhances understanding of pottery evolution patterns directly through visual analysis. The effectiveness and efficiency of our proposed method are evaluated by validating it on three distinct era division cases using data from the Dabagou and Miaozigou archaeological sites, which represent the Miaozigou culture and exhibit clear evolutionary patterns. Our method identifies representative artifacts for each era and uncovers their evolutionary patterns effectively and efficiently, achieving conclusions comparable to those of experts while significantly reducing time compared to traditional manual methods. [ABSTRACT FROM AUTHOR]

Recent years have seen increased interest in object detection‐based applications for fire detection in digital images and videos from edge devices. The environment's complexity and variability often lead to interference from factors such as fire and smoke characteristics, background noise, and camera settings like angle, sharpness, and exposure, which hampers the effectiveness of fire detection applications. Limited picture data for fire and smoke scenes further challenges model accuracy and robustness, resulting in high false detection and leakage rates. To address the need for efficient detection and adaptability to various environments, this paper focuses on (1) proposing a cloud‐edge collaborative architecture for real‐time fire and smoke detection, incorporating an iterative transfer learning strategy based on user feedback to enhance adaptability; (2) improving the detection capabilities of the base model YOLOv8 by enhancing the data augmentation method and introducing the coordinate attention mechanism to improve global feature extraction. The improved algorithm shows a 2‐point accuracy increase. After three iterations of transfer learning in the production environment, accuracy improves from 93.3% to 96.4%, and mAP0.5:0.95 increases by nearly 5 points. This program effectively addresses false detection issues in fire and smoke detection systems, demonstrating practical applicability. [ABSTRACT FROM AUTHOR]

Due to the security weaknesses of chaos-based pseudorandom number generators, in this paper, a new pseudorandom number generator (PRNG) based on mixing three-dimensional variables of a cat chaotic map is proposed. A uniformly distributed chaotic sequence by a logistic map is used in the mixing step. Both statistical tests and a security analysis indicate that our PRNG has good randomness and is more complex than any one-dimensional variable of a cat map. Furthermore, a new image encryption algorithm based on the chaotic PRNG is provided to protect the content of artwork images. The core of the algorithm is to use the sequence generated by the pseudorandom number generator to achieve the process of disruption and diffusion of the image pixels, so as to achieve the effect of obfuscation and encryption of the image content. Several security tests demonstrate that this image encryption algorithm has a high security level. [ABSTRACT FROM AUTHOR]

Digitization of Natural History Collections (NHCs) and mobilization of their data are pivotal for their study, preservation, and accessibility. Furthermore, thanks to digitization and mobilization, Natural History Museums can better showcase their collections, potentially attracting more visitors. However, the optimization of digitization workflows, especially when addressing small and/or historical NHCs, remains a challenge. Starting from a practical example, this contribution aims at providing a general guideline for the digitization of historical NHCs, with a particular focus on pre-digitization planning, during which some decisions should be made for ensuring a smooth, cost- and time-effective digitization process. The digitization of the algarium by Aristocle Vatova and Victor Schiffner was carried out following an image-to-data workflow, which allowed for reducing the handling of the specimens. The metadata were organized according to the Darwin Core standard scheme, and, together with the digital images of the specimens, have been made available to the scientific community and to the general public via an online portal. Thanks to the application of digital technologies and standardized methods, the accessibility of the collection has been enhanced, and its integration with historical data is possible, highlighting the relevance of shared experiences and protocols in advancing the digital transformation of natural history heritage. [ABSTRACT FROM AUTHOR]