Search

We propose a steganographic scheme based on permutations, which improves the capacity of embedding information in a series of p host binary images. Given a host binary image block of size m x n bits and any embedding technique T, where T can hide Q(m, n) bits of data in the image; given p images, T can hide p x Q(m, n) bits of data in these images. Our scheme improves the capacity of embedding information in p images such that, instead of p x Q(m, n) bits, it can hide p x log2(p) + p x Q(m, n)bits. The results which have been obtained by experiments, show that our model performs a better hiding process in terms of hiding capacity.

Teledermatology is one of the most illustrious applications of telemedicine and e-health. In this field, telecommunication technologies are utilized to transfer medical information to the experts. Due to the skin's visual nature, teledermatology is an effective tool for the diagnosis of skin lesions especially in rural areas. Furthermore, it can also be useful to limit gratuitous clinical referrals and triage dermatology cases. The objective of this research is to classify the skin lesion image samples, received from different servers. The proposed framework is comprised of two module, which include the skin lesion localization/segmentation and the classification. In the localization module, we propose a hybrid strategy that fuses the binary images generated from the designed 16-layered convolutional neural network model and an improved high dimension contrast transform (HDCT) based saliency segmentation. To utilize maximum information extracted from the binary images, a maximal mutual information method is proposed, which returns the segmented RGB lesion image. In the classification module, a pre-trained DenseNet201 model is re-trained on the segmented lesion images using transfer learning. Afterward, the extracted features from the two fully connected layers are down-sampled using the t-distribution stochastic neighbor embedding (t-SNE) method. These resultant features are finally fused using a multi canonical correlation (MCCA) approach and are passed to a multi-class ELM classifier. Four datasets (i.e., ISBI2016, ISIC2017, PH2, and ISBI2018) are employed for the evaluation of the segmentation task, while HAM10000, the most challenging dataset, is used for the classification task. The experimental results in comparison with the state-of-the-art methods affirm the strength of our proposed framework.

In order to deal with the problems of low detection accuracy and efficiency existing in traditional detection methods of body behavior characteristics in sports training, this paper proposes a new detection method of body behavior characteristics in sports training based on the grey correlation model. According to this method, the foreground binary image is obtained by the interframe difference method, and the action information and contour information are extracted, firstly. And then, the behavior feature descriptor is obtained. After the description of body behavior characteristics in sports training is completed, the grey correlation coefficient is calculated, and the complete observation equation of time delay estimation of image grey value under complex sports training background is established to complete the detection of body behavior characteristics. The experimental results show that, compared with the traditional methods, the detection accuracy and efficiency of the text method can always maintain a high level, indicating that the practical application performance of this method is strong. In fact, the grey analysis does not attempt to find the best solution but does provide techniques for determining a good solution.

Shape classification from binary images is a challenging task within the computer vision community. Commonly, contour and structural features are computed to describe the objects and code patterns robust against rotation, scaling, and shape deformation. However, current techniques get a high-dimensional feature space decreasing the system performance and the attribute interpretability. Here, we introduce an enhanced and interpretable feature representation approach to support shape classification from binary images. Our method, named EIFR, employs a bag of contour fragments-based feature estimation, intrinsically robust to occlusion and shape deformation. Then, a ReliefF-based feature selection is applied to filter non-discriminative attributes. In turn, a kernel-alignment-based projection is used to measure the feature relevance enhancing the data representation through the matching between a similarity matrix computed from filtered attributes and a kernel matrix built from the shape labels. Attained results on benchmark datasets prove that EIFR improves the curvature-based features’ interpretability and favors the classification performance.

In tradition, surface mounted devices (SMD) are classified and registered manually in surface mount technology (SMT). Manual classification is inefficient and relies on the experience of the operators. We propose a novel SMD classification method based on a mixture neural network. The network contains two modules, one is a convolutional neural network with a gray image as input, and the other is a fully connected network with a Hand-Crafted feature as input. The lighting environment of chip has a great impact on chip imaging, and the classification method should maintain sufficient robustness against light changes in SMT. However, there is a lack of a robust feature extraction method for SMT classification against illumination changes. A novel feature extraction method based the characteristics of the binary chip image is first proposed, which is composed of the mathematical statistical pin parameters of SMD. As the light changes, the binary image is relatively stable, making the proposed feature is invariant to light changes. An SMD dataset in SMT contains 61 kinds of chips is built for training and testing. Experiments on this dataset demonstrate that our method is more effective than the state-of-the-art methods in terms of performance measures.

The microstructure is the key factor for quality discriminate of coke. In view of the characteristics of coke optical tissue (COT), a segmentation method of coke microstructures based on adaptive clustering was proposed. According to the strategy of multiresolution, adaptive threshold binarization and morphological filtering were carried out on COT images with lower resolution. The contour of the COT body was detected through the relationship checking between contours in the binary image, and hence, COT pixels were picked out to cluster for tissue segmentation. In order to get the optimum segmentation for each tissue, an advanced K -means method with adaptive clustering centers was provided according to the Calinski-Harabasz score. Meanwhile, Euclidean distance was substituted with Mahalanobis distance between each pixel in HSV space to improve the accuracy. The experimental results show that compared with the traditional K -means algorithm, FCM algorithm, and Meanshift algorithm, the adaptive clustering algorithm proposed in this paper is more accurate in the segmentation of various tissue components in COT images, and the accuracy of tissue segmentation reaches 94.3500%.

Binarization, one of the most popular research directions in computer vision, is still facing challenges, especially for the degraded historical Tibetan document images. Quite a few U-Net-based binarization approaches might encounter a particular problem called pseudo-touching which hampers subsequent procedures including text line segmentation, character segmentation, and recognition. To avoid these undesired pseudo-touching strokes and obtain optimal binary images, the present work employs several easy-to-use techniques, such as rescaling the input and output of the attention U-Net. Furthermore, we provide insights into the accelerated construction of the training set and discuss the effects of various configurations. The quantitative experimental results on our dataset show that upsampling the input image by a factor of two during the inference phase can alleviate the pseudo-touching. It achieves an average P-FM of 97.73 which is two percentage points higher than the result of U-Net. The proposed approach can also accept common challenges including non-uniform illumination, stains, noise and delivers finer performance across several metrics.

Automatic detection of a falling person based on noncontact sensing is a challenging problem with applications in smart homes for elderly care. In this article, we propose a radar-based fall detection technique based on time-frequency analysis and convolutional neural networks. The time-frequency analysis is performed by applying the short-time Fourier transform to each radar return signal. The resulting spectrograms are converted into binary images, which are fed into the convolutional neural network. The network is trained using labeled examples of fall and nonfall activities. Our method employs high-level feature learning, which distinguishes it from previously studied methods that use heuristic feature extraction. The performance of the proposed method is evaluated by conducting several experiments on a set of radar return signals. We show that our method distinguishes falls from nonfalls with 98.37% precision and 97.82% specificity, while maintaining a low false-alarm rate, which is superior to existing methods. We also show that our proposed method is robust in that it successfully distinguishes falls from nonfalls when trained on subjects in one room, but tested on different subjects in a different room. In the proposed convolutional neural network, the hierarchical features extracted from the radar return signals are the key to understand the fundamental composition of human activities and determine whether or not a fall has occurred during human daily activities. Our method may be extended to other radar-based applications such as apnea detection and gesture detection.

For the classification of mixed particle with imaging method, the traditional processing techniques tend to extract the particle features from binary images, where particles can be classified by combining feature design corresponding to the particle type and classifiers, such as BP neural network and Support Vector Machine (SVM). However, the accuracies of these methods would be seriously influenced by particle agglomeration and imprecise feature design. In the work, the convolutional neural network (CNN) was introduced to extract the particle features in the image, where the particle localizations were obtained by implementing the region proposal network (RPN). Meanwhile, the particle segmentation at pixel level was achieved by a developed classifier and a fully convolutional network. A series of experiments were performed to a flowing mixed particle system consisting of spherical, elongated and irregular particles, and it showed that both the average accuracy and recall rate of SVM method were up to 87% with artificial feature design, while they were increased to 97% and 93% with CNN, respectively. For the median diameter (Dn50) of irregular particles, the latter method can also reduce the analysis error by more than 11%. It revealed that some shortages like imprecise feature design in traditional methods can be covered, and an end-to-end classified system can be formed to provide a more effective way for online analysis of flowing mixed particles.

In this paper, we propose a novel vector-form image descriptor that measures the so-called Q-concavity of a binary image under all possible positions of a sliding window of fixed size. In this way, a local Q-concavity histogram (LQH) is created. We propose three techniques to speed up the process of obtaining such histograms. Then, we also present a strategy to determine the proper window size and the appropriate number of histogram bins to achieve the greatest classification power of the descriptor. To show another application of the descriptor, we also solve a binary image reconstruction problem using LQH as prior information. The reconstruction is formulated as a discrete global optimization problem, which is then solved by simulated annealing. We also conduct experiments to show the usefulness of this approach.

Reservoir fractures are essential locations to gather oil and gas. Recently, imaging logging technology has become a mainstream method for obtaining stratigraphic information. This paper proposed a combined optimal path search strategy to effectively identify and extract the fracture information in well logging images. Specifically, the threshold segmentation of logging images is used to obtain the binary image. In addition, the identification of connected fractures in the logging image is transformed into the optimal path search, and the identification and extraction of reservoir fractures are realized by constructing the optimal path between the two ends of fractures. Finally, an improved ant colony algorithm is applied to filter irrelevant information and extract fractures automatically by recording all the ants’ exploration trajectories in the ant colony. Compared with previous approaches, the proposed method can eliminate irrelevant background features and merely reserve pixels corresponding to fractures. Simultaneously, relative to the conventional strategy, the time consumption is reduced by more than 98%. The findings of this study can help for better extracting fractures automatically and reducing manual workload.

Sketches in existing large-scale datasets like the recent QuickDraw collection are often stored in a vector format, with strokes consisting of sequentially sampled points. However, most existing sketch recognition methods rasterize vector sketches as binary images and then adopt image classification techniques. In this article, we propose a novel end-to-end single-branch network architecture RNN-Rasterization-CNN ( Sketch-R2CNN for short) to fully leverage the vector format of sketches for recognition. Sketch-R2CNN takes a vector sketch as input and uses an RNN for extracting per-point features in the vector space. We then develop a neural line rasterization module to convert the vector sketch and the per-point features to multi-channel point feature maps, which are subsequently fed to a CNN for extracting convolutional features in the pixel space. Our neural line rasterization module is designed in a differentiable way for end-to-end learning. We perform experiments on existing large-scale sketch recognition datasets and show that the RNN-Rasterization design brings consistent improvement over CNN baselines and that Sketch-R2CNN substantially outperforms the state-of-the-art methods.

In this paper, a rose-flower variety classification scheme, using color and shape features is presented. The first three statistical moments of the R, G, and B planes of the image were calculated to describe the color, while Fourier coefficients are used to describe the shape. For shape description, signatures (wave-forms) of the boundary contour of the binary images were extracted. Fourier coefficients that are used to describe the shape were estimated using the signatures generated. Depending on the Fourier coefficients, a representation of sums of angles formed along boundaries of the flowers was defined. Using these sums and the color features as input to an artificial neural network (ANN), the flowers were classified into their respective target classes. The eighteen flower varieties considered in this study were classified with an accuracy of 95.6%, 98.9%, and 100% using their shape, color, and combination of both shape and color features, respectively. Comparing these results, it was found that the combination of the two features is an efficient criterion for rose flower variety discrimination and classification.

Cell counting plays a vital role in biomedical researches. However, manual cell counting is time-consuming, laborious, and low efficiency and has a high counting error rate problem. An automatic counting approach for Hela cells of phase-contrast microscopic images is proposed based on the combination of Otsu and watershed segmentation methods to solve the mentioned issues. Firstly, image preprocessing is performed. Secondly, the Otsu method was used to obtain an automatic global optimal threshold for segmentation to achieve batch counting of images. Thirdly, the marker watershed was performed to separate adherent cells and to avoid over-segmentation simultaneously. Finally, cells in phase-contrast microscopic images were counted by detecting the numbers of connected domains in the binary image. Taking the manual counting result as the counting standard and MIS, INC, and ACC are used as evaluation indicators. The experimental results showed that the average values of MIS, INC, and ACC of the proposed method are only 3.31%, 3.49%, and 96.69%, respectively. Additionally, each cell image was counted only takes 0.65 s on averagely. To further test the performance of the proposed method, a comparative experiment was carried out by Image J, and the result shows that the proposed method has a better counting performance with a higher average accuracy of 96.55% to Image J with 93.39%.The proposed method for cell counting is simple, feasible, fast and high accurate, and it can be used as an effective method for cell counting of the phase-contrast microscopic images.

Background: Cardiac arrhythmias are considered as one of the most serious health conditions; therefore, accurate and quick diagnosis of these conditions is highly paramount for the electrocardiogram (ECG) signals. Moreover, are rather difficult for the cardiologists to diagnose with unaided eyes due to a close similarity of these signals in the time domain. Objective: In this paper, an image-based and machine learning method were presented in order to investigate the differences between the three cardiac arrhythmias of VF, VT, SVT and the normal signal.Material and Methods: In this simulation study, the ECG data used are collected from 3 databases, including Boston Beth University Arrhythmias Center, Creighton University, and MIT-BIH. The proposed algorithm was implemented using MATLAB R2015a software and its simulation. At first, the signal is transmitted to the state space using an optimal time delay. Then, the optimal delay values are obtained using the particle swarm optimization algorithm and normalized mutual information criterion. Furthermore, the result is considered as a binary image. Then, 19 features are extracted from the image and the results are presented in the multilayer perceptron neural network for the purpose of training and testing. Results: In order to classify N-VF, VT-SVT, N-SVT, VF-VT, VT-N-VF, N-SVT-VF, VT-VF-SVT and VT-VF-SVT-N in the conducted experiments, the accuracy rates were determined at 99.5%, 100%, 94.98%, 100%,100%, 100%, 99.5%, 96.5% and 95%, respectively. Conclusion: In this paper, a new approach was developed to classify the abnormal signals obtained from an ECG such as VT, VF, and SVT compared to a normal signal. Compared to Other related studies, our proposed system significantly performed better.

An algorithmic support for metallographic images preprocessing and analysis is presented. The software product implements metallographic methods for the grain size determination by comparison of rating scales, counting beans, calculation of grain boundaries intersections for equiaxed and elongated grains, measuring a chords length. Multiple digital images can be used as initial data. Pre-processing is used to remove noise, sharpen and improve contrast using Adaptive Contrast-Limiting Histogram Equalization (CLAHE). The next step is grain segmentation. A combination of distance transform and adaptive watershed binarization is used. Binary images filtration based on the operations of mathematical morphology is provided. Contour analysis is used to determine grain boundaries. The study’s results of the entire rating scales and on the real metallographic images are presented. High efficiency of an algorithmic support is confirmed by the experiments. The software implementation has the following main features: the ability to calibrate the actual grain size, automatic or manual image preprocessing, grain size analysis with saving the results as a report in jpg format. Batch processing provides the ability to download images for processing with the same type of algorithm.

Layout hotspot detection is of great importance in the physical verification flow. Deep neural network models have been applied to hotspot detection and achieved great successes. The layouts can be viewed as binary images. The binarized neural network (BNN) can thus be suitable for the hotspot detection problem. In this article, we propose a new deep learning architecture based on BNNs to speed up the neural networks in hotspot detection. A new binarized residual neural network is carefully designed for hotspot detection. Experimental results on ICCAD 2012 and 2019 benchmarks show that our architecture outperforms previous hotspot detectors in detecting accuracy and has an $8\times $ speedup over the best deep learning-based solution. Since the BNN-based model is quite computationally efficient, a good tradeoff can be achieved between the efficiency and performance of the hotspot detector by applying ensemble learning approaches. Experimental results show that the ensemble models achieve better hotspot detection performance than the original with acceptable speed loss.

In the existing multimodal biometric authentication technique, there is no integrity in the biometric information, and authentication of end users is also not very secured. In this paper, we propose Fisher-Yates Chaotic Shuffling based Visual Cryptography Scheme (FYCS-VCS) for Multimodal Biometric Authentication. The proposed approach enhances the security of multimodal biometric images by protecting the individual shares which supports in maintaining the integrity and confidentiality. Also by the combination of FYCS –VCS Scheme the intruders cannot view and modify shares without knowing the sequential order of the shares. In this technique, initially two or three (finger print, Iris, Face) biometric modalities are considered and fused into a binary image using Histogram of Oriented Gradients (HOG) and Low-Rank Representation (LRR) scheme.Then using (k, n) VSS scheme, n shares of the binary image is created which are encrypted by applying Fisher-Yates Chaotic Shuffling algorithm.. The shares are reconstructed back by applying reverse of Yates-Shuffling algorithm, to generate the fused image. By extracting the HOG features from the fused image, the respective biometric images are obtained. The reconstructed biometric images are authenticated against the original images of the person by an authentication server. The proposed FYCS-VCS multimodal biometric authentication scheme is implemented in MATLAB and is compared against the VSS scheme. Experimental results have shown that FYCS-VCS attain lesser MSE and higher PSNR values when compared to VSS. Proposed approach reduces storage cost and time complexity.

In automatic cancer detection, nuclei segmentation is a very essential step which enables the classification task simpler and computationally more efficient. However, automatic nuclei detection is fraught with the problems of inter-class variability of nuclei size and shapes. In this research article, a novel unsupervised edge detection technique, is proposed for segmenting the nuclei regions in liver cancer Hematoxylin and Eosin (H&E) stained histopathology images. In this novel edge detection technique, the notion of computing local standard deviation is incorporated, instead of computing gradients. Since, local standard deviation value is correlated with the edge information of image, this novel method can extract the nuclei edges efficiently, even at multiscale. The edge-detected image is further converted into a binary image by employing Ostu (IEEE Trans Syst Man Cybern 9(1):62–66, 1979)’s thresholding operation. Subsequently, an adaptive morphological filter is also employed in order to refine the final segmented image. The proposed nuclei segmentation method is also tested on a well-recognized multi-organ dataset, in order to check its effectiveness over wide variety of dataset. The visual results of both datasets indicate that the proposed segmentation method overcomes the limitations of existing unsupervised methods, moreover, its performance is comparable with the same of recent deep neural models like DIST, HoverNet, etc. Furthermore, three quality metrics are computed in order to measure the performance of several nuclei segmentation methods quantitatively. The mean value of quality metrics reveals that proposed segmentation method indeed outperformed other existing nuclei segmentation methods.

Recognition of overlapping objects is required in many applications in the field of computer vision. Examples include cell segmentation, bubble detection and bloodstain pattern analysis. This paper presents a method to identify overlapping objects by approximating them with ellipses. The method is intended to be applied to complex-shaped regions which are believed to be composed of one or more overlapping objects. The method has two primary steps. First, a pool of candidate ellipses are generated by applying the Euclidean distance transform on a compressed image and the pool is filtered by an overlaying method. Second, the concave points on the contour of the region of interest are extracted by polygon approximation to divide the contour into segments. Then, the optimal ellipses are selected from among the candidates by choosing a minimal subset that best fits the identified segments. We propose the use of the adjusted Rand index, commonly applied in clustering, to compare the fitting result with ground truth. Through a set of computational and optimization efficiencies, we are able to apply our approach in complex images comprised of a number of overlapped regions. Experimental results on a synthetic data set, two types of cell images and bloodstain patterns show superior accuracy and flexibility of our method in ellipse recognition, relative to other methods.

We present a simple end-to-end model based on deep learning to automatically decompose sketched objects into components by disentangling the visual representation. The performance of visual representation learning based models degrades as categories increase. Rather than building a mapping from a static image to the whole sketch sequences, we propose an interpretable disentangled representation of sketch to understand component concepts and the relationship among such concepts. Our model takes the binary image of a sketched object and produces a component stroke sequence set corresponding to key components in the sketch. Experiments show that our method significantly outperforms all baselines quantitatively at the degree of disentanglement, and our method is more stable while training on tens of categories.

Due to many classical numerical methods have not yet mature quantum counterparts, the quantum circuits design for quantum image processing is very important. In this paper, using the novel enhanced quantum image representation (NEQR) model and the crossing number (CN) minutiae detection method, quantum circuits for fingerprint minutiae extraction are designed, which is focus on extracting ridge endings and ridge bifurcations from thinned binary fingerprint image. In order to improve the performance of the whole system, the quantum circuits for detection and elimination the false minutiae among the extracted minutiae are also constructed.

This paper presents a partially connected Multilayer Perceptron (PCM) neural network as an optimal new MLP with a supervised algorithm and three hidden layers to detect face emotions. Compared with the traditional MLP, the proposed network shows improvements in speed, accuracy, and computational time. Six emotions have been considered in this study, namely anger, surprise, fear, sadness, normal, and happiness. The image dataset with the fixed background is used to test and train the network. Canny edge detection algorithm is employed to separate regions of the face including eyes, mouth, and eyebrows from the background. A binary image is extracted to represent the areas of eye, mouth, and eyebrow. The feature extraction is carried out by Legendre coefficients of Legendre polynomials which are selected for the best accuracy. Results show that the partial network is faster and has a lower computational complexity compared with the full connection network. It also has a faster convergence with higher accuracy.

It is difficult to detect forest fires in complex backgrounds owing to the many interfering factors in forest fire smoke. In this paper, a novel method that combines Time Domain Robust Principal Component Analysis (TRPCA) and a Two-Stream Composed of Visual Geometry Group Network (VGG) and Bi-Long Short-Term Memory (BLSTM) (TSVB) model is proposed for forest fire smoke detection. First, features are extracted from the smoke video from the spatial stream (static) and time stream (dynamic). For the spatial stream, static features are extracted from a single-frame image of the smoke video using the VGG network. For the time stream, continuous-frame binary images of the smoke are obtained using the TRPCA algorithm. Then, the dynamic features of the smoke are extracted by VGG and BLSTM. Finally, the static and dynamic features are fused using a concatenate function to achieve forest fire smoke detection. The experimental results show that compared with the single-feature model, the proposed method effectively improves learning ability and prediction ability, and shows strong robustness against interference factors in a complex background, with accuracy of forest fire smoke detection reaching 90.6%.

In Cultural Heritage inquiries, a common requirement is to establish time-based trends between archaeological artifacts belonging to different periods of a given culture, enabling among other things to determine chronological inferences with higher accuracy and precision. Among these, pottery vessels are significantly useful, given their relative abundance in most archaeological sites. However, this very abundance makes difficult and complex an accurate representation, since no two of these vessels are identical, and therefore classification criteria must be justified and applied. For this purpose, we propose the use of deep learning architectures to extract automatically learned features without prior knowledge or engineered features. By means of transfer learning, we retrained a Residual Neural Network with a binary image database of Iberian wheel-made pottery vessels’ profiles. These vessels pertain to archaeological sites located in the upper valley of the Guadalquivir River (Spain). The resulting model can provide an accurate feature representation space, which can automatically classify profile images, achieving a mean accuracy of 0.96 with an f -measure of 0.96 . This accuracy is remarkably higher than other state-of-the-art machine learning approaches, where several feature extraction techniques were applied together with multiple classifier models. These results provide novel strategies to current research in automatic feature representation and classification of different objects of study within the Archaeology domain.

Binarization is an important step for most of document analysis systems. Regarding music score images with a complex background, the existence of background clutters with a variety of shapes and colors creates many challenges for the binarization. This paper presents a model for binarization of the complex background music score images by fusion of deep convolutional neural networks. Our model is directly trained from image regions using pixel values as inputs and the binary ground truth as labels. By utilizing the generalization capability of the residual network backbone and useful feature learning ability of dense layer, the proposed network structures can differentiate foreground pixels from background clutters, minimize the possibility of overfitting phenomenon and thus can deal with complex background noises appearing in the music score images. Comparing to traditional algorithms, binary images generated by our method have a cleaner background and better-preserved strokes. The experiments with captured and synthetic music score images show promising results compared to existing methods.

HighlightsChlorophyll fluorescence imaging can be used to evaluate chilling injury.Chilling injury area heterogeneity in the L*a*b* color space is significant.Improved k-means++ clustering has a good segmentation effect on chilling injury.Abstract. The application of fluorescence imaging in the detection of tomato chilling injury was investigated. With the segmentation of the chilling injury area serving as the experimental target, an algorithm based on chlorophyll fluorescence image analysis and improved k-means++ clustering was proposed. First, the extraction of lateral heterogeneity values algorithm was used to analyze the horizontal heterogeneity in five color spaces of the fluorescence images of tomato seedling leaves, and it was found that the chilling injury area was significant in the L*a*b* color space. Second, the fluorescence image was converted from the RGB color space to the L*a*b* color space, and the k-means++ algorithm was used to cluster the two-dimensional data of the a*b* space. Third, insertion sorting was used to reorder the different label regions obtained by the k-means++ clustering algorithm, and the region with the largest value was used as the target region. Finally, the binary image of the target region was filtered using a morphological noise filter, and the cold-damaged area was outputted by the mask operation. The results showed that the cold-damaged area was well segmented when the fluorescence imaging contained yellow cold traces. The mean match rate of the proposed algorithm was 37.08%, 13.52%, and 0.96% higher than that based on the HSV model and watershed algorithm, the fuzzy C-means clustering method, and the k-means clustering method, respectively. Similarly, the mean error rate was 13.69%, 5.56%, and 0.16% lower than that based on the HSV model and watershed algorithm, the fuzzy C-means clustering method, and the k-means clustering method, respectively. These findings provide a foundation for research on early warning of chilling injury by identifying the chilling injury status of tomato leaves using a computer vision method. Keywords: Chlorophyll fluorescence, Fluorescence image, Image segmentation, k-Means++.

This paper aims to acquire the crack information from the sound production images in vocal music in an accurate and comprehensive manner. Firstly, the image processing technology based on partial differential equations was introduced, and the principle of wavelet model was expounded. Considering the defects of the wavelet model, an improved wavelet model was constructed based on image enhancement function. The improved model was applied to process the sound production images in vocal music, which contain single crack or multiple cracks, respectively, producing high-quality binary images on the cracks of sound production in vocal music. The binary images were quantified to obtain the characteristic parameters of the sound source in vocal music, laying the basis for further research into sound production in vocal music. To verify its effectiveness, the improved wavelet model was compared with the traditional wavelet model through simulation experiment. The results show that the improved wavelet model achieved better image segmentation effect and quantified the microstructure of the sound source more accurately than the traditional wavelet model. Finally, the authors proved that the proposed model can be used to compute the coefficients of sound production with cracks and the damage variables of microstructure.

In recent years, face detection has been widely applied to a variety of fields, such as face recognition, image focusing, and surveillance systems. This study proposes a real-time multi-faces detection system based on naive Bayesian classifier using Field Programmable Gate Array (FPGA). The system includes three main parts, feature extraction, candidate face detection, and false elimination. First, downscale the image to the image pyramid and extract local binary image features from each downscaling image. With the bit-plane slicing for Local Binary Pattern (LBP) can save the memory consumption and speed up the computation. Then, adopt the naive Bayesian classifier to identify candidate faces. Finally use skin color filter and face overlapping elimination to remove false positives. The experimental results show that the accuracy rate is up to 96.14% in face detection, which demonstrates the proposed real-time multi-faces detection system is indeed effective and efficient.

Scene text analysis involves detecting and processing text/words in natural scene images for serving various purposes. This problem domain intrigues the research fraternity due to challenges like dealing with noise, blur, heterogeneous intensity variation, etc. The ultimate goal is making detected scene word recognizable by any standard Optical Character Recognition system, thereby necessitating effective scene word binarization. Several methods address scene text detection, but comparatively few addresses scene word binarization. These binarization methods, however, have limitations in robustness against image quality-based complexities thus causing low precision. Here, a novel approach is proposed for scene word binarization called Bi-level Overlapped Binning where intensities of color channels R, G and B are grouped or binned to generate several solutions in the form of binary images. The stable binary images are identified such that the image solutions from them can be classified as text or non-text using a standard classifier trained with some popular features. Finally, the resultant text solutions are combined probabilistically to get the binarized output. The proposed method is evaluated on standard datasets such as SVT, ICDAR-2003, ICDAR-2011 (Scene), ICDAR-2011 (BDI), KAIST and Total-Text achieving precisions 0.76, 0.87, 0.89, 0.85, 0.84 and 0.87 respectively, which are mostly better than that of the state-of-the-art.

Road detection from the satellite images can be considered as a classification process in which pixels are divided into the road and non-road classes. In this research, an automatic road extraction using an artificial neural network (ANN) based on automatic information extraction from satellite images and self-adjusting of the hidden layer proposed. Parameters of non-urban road networks from satellite images using a histogram-based binary image segmentation technique are also presented. The segmentation method is implemented by determining a global threshold, which is obtained from a statistical analysis of a number of sample satellite images and their ground truths. The thresholding method is based on two major facts: first, the points corresponding to non-asphalt roads are brighter than other areas in non-urban images. Second, it is observed that in an aerial image, the area covered by roads is only a small fraction of total pixels. It is also observed that pixels corresponding to roads are generally populated at the very bright end of the image greyscale histogram. In this method, at first, the possible road pixels are selected by the proposed segmentation method. Then different parameters, including color, gradient, and entropy, are computed for each pixel from the source image. Finally, these features are used for the artificial neural network input. The results show that the accuracy of the proposed road extraction method is around 80%.

Objective: To achieve the accurate segmentation of ovarian cyst from the ultrasound images. Method: Ovarian cyst ultrasound images are taken from ultrasound images.com and sonoworld.com. The cysts are segmented using adaptive thresholding technique. The segmented image (binary image) is divided into sub blocks and then number of binary transition in each block is calculated. Based on the number of transition, the pixel values are replaced by 0 or the same pixel value is maintained. In order to measure the performance of the proposed enhancer various measures like Accuracy (ACC), Dice Coefficient (DC), Jaccard Similarity Index (JSI), Matthews correlation coefficient (MCC), Sensitivity, Specificity and Precision are measured. Findings: In order to analyse the performance of the enhancer with adaptive thresholding technique, 100 ultrasound ovarian cyst images are taken. The enhancer produced better result than the existing adaptive thresholding technique. Novelty/Application: The proposed enhancer enriches the quality of the ovarian cyst segmentation. Keywords: Segmentation; adaptive thresholding technique; ultrasound images; poly cystic ovarian syndrome; follicle; ovarian cyst

A system using computer assistance in the matching of the callosity patterns of individual southern right whales is described. Whenprovided with a digitised representation of an individual whale’s callosity pattern, the prototype system produces a hierarchical output ofthe most similar patterns in the database with relatively high accuracy. A trial database of binary images of the callosity patterns of 165individually identified southern right whales was created. A further two replicates each of nine different individual whales within the trialdatabase, were then created by two different operators, producing a test set of 18 images. A software program, utilising a pattern recognitionalgorithm and incorporating a mouse driven user interface, was developed so that when provided with a binary bitmap of an individualwhale from the test set, the program compares it against a trial database of previously saved bitmaps and produces a hierarchical outputof the most similar whales, or nearest ‘matches’. For 15 of the 18 test images (83%), the system returned the correct whale as the top matchout of the 165 in the trial database. For the remaining three test images the correct whale was the second, sixth and sixteenth ranked whalein the trial database containing 165 whales. The program was successful in reducing the number of individuals required for manualcomparison to a small percentage of the total catalogue, with a high degree of accuracy, and with a significant associated time saving. Itis envisaged that the final matching will continue to be done visually by an experienced operator using the original photographs. Furtherrefinement of the system with the aim of streamlining and simplifying the input process and incorporating partial pattern recognition isintended.

Histogram is an important data chart that is commonly present in scientific documents. In this paper, an automatic histogram detection and information extraction methodology, based on Hough line detector and Morphological operator, is proposed. The proffered system is comprised of three steps: pre-processing, axis detection, and chart pattern extraction. In the pre-processing step, the RGB image pattern of a histogram is converted into a binary image. Next, in the axis detection step, horizontal axis, vertical axis and title of the histogram are extracted. In this step Hough line detector methodology was applied to detect horizontal and vertical lines in the image patterns. From the set of identified vertical lines, both the endpoints of a line, having the same minimum values of x co-ordinate was considered as a vertical axis. Similarly, from the set of identified horizontal lines, the two endpoints of a line having the same maximum values of y co-ordinate were considered as a horizontal axis. With respect to the dimensions of the horizontal axis and vertical axis, a rectangular region containing horizontal axis values and label, vertical axis values and label and title are extracted. In the final chart pattern extraction step, using morphological operations, the frequency of data present in the histogram was identified. Verification and validation tests of the propounded system yielded promising results, indicative of efficient approach for extraction of histogram information.

Tool marks on face-milled surfaces contain huge information about the manufacturing processes. Direct surface segmentation based on tool marks is in favor of surface error sources diagnoses. However, traditional surface segmentation methods are prone to over-segmentation when partition surfaces with tool marks. This paper proposes an improved segmentation approach to solve this problem. Based on surface topography measured by high definition metrology (HDM), the surface segmentation methodology mainly involves four steps: automatic subsurface selection, local thresh-holding, broken tool marks repairing and water segmentation (abbreviated as “STRW” methodology). A novel concept called “periodic degree” is proposed and used as the criteria of subsurface selection. A binary image of tool marks is created by an adaptive local threshold. Broken tool marks are identified by a distance threshold and repaired by a convex-hull based tool marks repairing algorithm. Finally, water segmentation is applied to divide the surface into different regions and each region belongs to a unique tool tooth trajectory. Three real cases from powertrain plant demonstrate the procedures of the methodology and verify the effectiveness of the proposed methodology.

Utilizing statistical models of binary images is a common and effective means to steganalyze binary images, and the design of the statistical model is essential to the performance of steganalysis. In this paper, we propose a new model based on a histogram of pixel structuring elements (SEs), which is a suitable representation of a binary image for the task of steganalysis. The texture property and the dependency among pixels are considered inside the SEs. The SEs with different patterns will be evaluated comprehensively according to a statistical criterion, and some of them will be selected to construct the feature set for training the steganalyzer. The distributions of these selected SEs, which contain many highly flippable pixels, will be emphasized by the criterion, and they can reflect the difference between cover images and stego-images. Finally, a series of experiments are conducted on two datasets, and the results show that the proposed scheme significantly outperforms state-of-the-art schemes.

Face recognition from an image/video has been a fast-growing area in research community, and a sizeable number of face recognition techniques based on texture analysis have been developed in the past few years. Further, these techniques work well on gray-scale and colored images, but very few techniques deal with binary and low-resolution images. As the binary image is becoming the preferred format for low face resolution analysis, there is a need for further studies to provide a complete solution for the image-based face recognition system with a higher accuracy rate. To overcome the limitation of the existing methods in extracting distinctive features in low-resolution images due to the contrast between the face and background, we propose a statistical feature analysis technique to fill the gaps. To achieve this, the proposed technique integrates the binary-level occurrence matrix (BLCM) and the fuzzy local binary pattern (FLBP) named FBLCM to extract global and local features of the face from binary and low-resolution images. The purpose of FBLCM is to distinctively improve performance of edge sharpness between black and white pixels in the binary image and to extract significant data relating to the features of the face pattern. Experimental results on Yale and FEI datasets validate the superiority of the proposed technique over the other top-performing feature analysis methods. The developed technique has achieved the accuracy of 94.54% when a random forest classifier is used, hence outperforming other techniques such as the gray-level co-occurrence matrix (GLCM), bag of word (BOW), and fuzzy local binary pattern (FLBP), respectively.

Efficient matching of local image features is a fundamental task in many computer vision applications. However, the real-time performance of top matching algorithms is compromised in computationally limited devices, such as mobile phones or drones, due to the simplicity of their hardware and their finite energy supply. In this paper we introduce BEBLID, an efficient learned binary image descriptor. It improves our previous real-valued descriptor, BELID, making it both more efficient for matching and more accurate. To this end we use AdaBoost with an improved weak-learner training scheme that produces better local descriptions. Further, we binarize our descriptor by forcing all weak-learners to have the same weight in the strong learner combination and train it in an unbalanced data set to address the asymmetries arising in matching and retrieval tasks. In our experiments BEBLID achieves an accuracy close to SIFT and better computational efficiency than ORB, the fastest algorithm in the literature.

In this paper, a novel method for binary image comparison is presented. We suppose that the image is a set of transactions and items. The proposed method applies along rows and columns of an image; this image is represented by all frequent itemset. Firstly, the rows of the image are considered as transactions and the columns of the image are considered as items. Secondly, we considered rows as items and columns as transactions. Besides, we also apply our technique to color image; firstly we segment the image and each segmented region is considered as a binary image. The proposed method is tested on the MPEG7 database and compared with the moment’s method to show its efficiency.

To deal with problems of uncertain modulations and multiple pulse widths in pulse waveforms (PWs) during the identifying procedure, a novel specific emitter identification (SEI) method based on PW images (PWIs) and convolutional neural network is proposed. In the method, a more accurate signal model is built with considering the rising, steady and falling part of the whole PW based on actual radar pulse signals. PWI achieves transforming time-domain waveforms to 2D binary images as an SEI analysis feature. To match the PWI feature, a convolutional neural network with the small convolutional kernel is designed to extract the subtle features and finish the supervised training. By tuning the parameters of the convolutional neural network, it completes a balance of consuming time and identifying accuracy. Simulations and experiments indicate that the proposed method outperforms the existed methods on identifying radar individuals with uncertain modulations and multiple pulse widths in the intercepted pulse signals.

As an important task in the process of image understanding and analysis, saliency detection has recently received increasing attention. In this paper, we propose an efficient multiple self-weighted graph-based manifold ranking method to construct salient maps. First, we extract several different views of features from superpixels, and generate original salient regions as foreground and background cues using boundary information via multiple graph-based manifold ranking. Furthermore, a set of hyperparameters is learned to distinguish the importance between different graphs, which can be viewed as an adaptive weighting of each graph, and then a centroid graph is generated by using these self-weighted multiple graphs. An iterative algorithm is proposed to simultaneously optimize the hyperparameters as well as the centroid graph connection. Thus, an ideal centroid graph can be obtained, offering a more clear profile of the separated structure. Finally, the saliency maps can be produced with an approximate binary image from the manifold ranking. Extensive experiments have demonstrated our method consistently achieves superior detection performance than several state-of-the-arts.

One of ways to increase the success of hatching eggs is by selecting and separating the eggs embryonated (fertile) with eggs are not embryonated (infertile) by way of observation (candling). This system utilizes digital image processing as an identification process. By this system, it is expected that the identification results will be more accurate results than conventional monitoring, so as to increase the results of hatching. This system utilizes a flashlight as a medium, so that the egg's internal condition can be seen which then takes pictures by the webcam. After that the digital image processing is done by converting the original image (RGB) to binary image by providing a thresholding value (T), the T value is very influential in the next image processing, opening and closing, thinning the image (thinning), and contour detection. Then from the final process of contour detection produces the number of detection of blood vessels that are considered as embryos as a determinant of the outcome category of identification. From the experiments carried out the percentage of conformity between the original condition of the egg with the results obtained in the system that is 88.88%, in determining the yield category (fertile/infertile) with an error of 11.12%. For the suitability of the estimated percentage of hatchlings themselves have a success of 61.11% with an error of 38.89%. These results are influenced by many factors like the condition of the eggs and supporting devices in the system.

A finger biometric system at an unconstrained environment is presented in this paper. A technique for hand image normalization is implemented at the preprocessing stage that decomposes the main hand contour into finger-level shape representation. This normalization technique follows subtraction of transformed binary image from binary hand contour image to generate the left-side of finger profiles (LSFPs). Then, XOR is applied to LSFP image and hand contour image to produce the right side of finger profiles. During feature extraction, initially, 30 geometric features are computed from every normalized finger. The rank-based forward–backward greedy algorithm is followed to select relevant features and to enhance classification accuracy. Two different subsets of features containing 9 and 12 discriminative features per finger are selected for two separate experimentations those use the ${k}$ -nearest neighbor and the random forest (RF) for classification on the Bosphorus hand database. The experiments with the selected features of four fingers except the thumb have obtained improved performances compared to features extracted from five fingers and also other existing methods evaluated on the Bosphorus database. The best identification accuracies of 96.56% and 95.92% using the RF classifier have been achieved for the right- and left-hand images of 638 subjects, respectively. An equal error rate of 0.078 is obtained for both types of the hand images.

A technique for face detection inthe image is proposed, which is based on binarization, scaling, and segmentation of the image, followed by the determination of the largest connected component that matches the image of the face. Modern methods of binarization, scaling, and taxonomic image segmentation have one or more of the following disadvantages: they have a high computational complexity; require the determination of parameter values. Taxonomic image segmentation methods may have additional disadvantages: they do not allow noise and outliers selection; clusters can’t have different shapes and sizes, and their number is fixed. Due to this, to improve the efficiency of face detection techniques, the methods of binarization, scaling and taxonomic segmentation needs to be improved. A binarization method is proposed, the distinction of which is the use of the image background. This allows to simplify the process of scaling and segmentation (since all the pixels in the background are represented by the same color), non-uniform brightness of the face, and not to use the threshold settings and additional parameters. A binary image scaling method is proposed, the distinction of which is the use of an arithmetic mean filter with threshold processing and fast wavelet transform. This allows to speed up the image segmentation process by about P2times, where P is the scaling parameter, and not to use the time-consuming procedure for determining. A binary scaled image segmentation method is proposed, the distinction of which is the use of density clustering. This allows to separate areas of the face of non-uniform brightness from the image background, noise and outliers. It also allows clusters to have different shapes and sizes, to not require setting the number of clusters and additional parameters. To determine the scaling parameter, numerous studies were conducted in this work, which concluded that the dependence of the segmentation time on the scaling parameter is close to exponential. It was also found that for small P, where P is the scaling parameter, the quality of face detection deteriorates slightly. The proposed technique for face detection in image based on binarization, scaling and segmentation can be used in intelligent computer systems for biometric identification of a person by the face image

Satellite image denoising is a recent trend in image processing, but faces many challenges due to the environmental factors. Previous works have developed many filters for denoising the hyperspectral satellite images. Accordingly, this work utilizes an adaptive filter with the type 2 fuzzy system and the optimization-based kernel interpolation for the satellite image denoising. Here, the image denoising has been done through three steps, namely noise identification, noise correction and image enhancement. Initially, the type 2 fuzzy system identifies the noisy pixels in the satellite image and converts the image into a binary image, which is passed through the adaptive nonlocal mean filter (ANLMF) for the noise correction. Finally, the kernel-based interpolation scheme carries out the image enhancement, which is done through the proposed chronological Jaya optimization algorithm (chronological JOA) that is developed by modifying Jaya optimization algorithm (JOA) with the chronological idea. The performance of the proposed denoising scheme is analyzed by considering the satellite images from two standard databases, namely Indian pines database and NRSC/ISRO satellite database. Also, the comparative analysis is performed with the state-of-the-art denoising methods using the evaluation metrics, peak signal to noise ratio (PSNR), structural similarity index (SSIM) and second derivative-like measure of enhancement (SDME). From the results, it is exposed that the proposed adaptive filter with the chronological JOA has the improved performance with the PSNR of 22.0408 dB, SDME of 244.133 dB and SSIM of 0.872.

Brain cancer is a major health problem that affects the lives of many people. Clinicians depend on their medical knowledge to analyse laboratory test results and clinical information extracted manually from medical images, to identify the essential characteristics of tumours such as size, shape, and location. The accurate diagnosis of brain tumours is very essential for deciding the most appropriate treatment protocols and procedures. Apart from being tedious, slow and time-consuming manual segmentation of brain image scans is also prone to human error. In order to enhance the accuracy and reliability of the diagnosis of brain tumours, rigorous image processing and segmentation is required. In this study the authors present an automated image segmentation method for detecting and localising multiple brain tumours of different sizes and intensities by using a technique of object counting coupled with an evaluation process. The object counting technique were carried out using multiple binary images with different threshold values, and the evaluation process was based on assessment criteria of specific tumour parameters. Different magnetic resonance images with multiple tumours were used for testing the proposed method. The results indicated that the proposed method is effective in detecting and localising multiple true tumours in the brain.