Search

This research presents a novel node-based Graph Convolutional Network (GCN) approach for the classification of breast cancer from ultrasound images. Utilizing the Simple Linear Iterative Clustering (SLIC) algorithm, superpixels are segmented and treated as nodes and connected based on color similarity and spatial proximity. This enables the graph data capturing both long-range and short-range dependencies among image features. The graph-structured data is processed through a multi-layer GCN, which effectively aggregates and learns from complex node interrelations to classify the nodes as benign, malignant, or normal. In the final stage, a voting rule is applied to the node classification in order to perform the final image-level classification. Overall, the proposed framework yielded impressive findings on two distinct datasets, Breast Ultrasound Images Dataset (BUSI) and Breast Ultrasound Image dataset from Brazil (BUSBRA). Different numbers of connections between nodes are evaluated to indicate the importance of hidden insight interconnections in the medical imaging domain. The results give an accuracy of 98.73% for the BUSI dataset and 98.40% in the case of the BUSBRA dataset, indicating superior performance compared to conventional and other advanced methodologies. This highlights the potential of employing node-based GCNs for breast cancer detection using ultrasound imagery in clinical applications.

The accurate and reliable derivation of the pap smear cell, which contains cytoplasm and nucleus regions, depends on the segmentation process employed in the cervical cancer detection mechanism. In this paper, an Improved Boykov’s Graph Cut-based Conditional Random Fields and Superpixel imposed Semantic Segmentation Technique (IBGC-CRF-SPSST) is proposed for efficient cervical cancer detection. This proposed IBGC-CRF-SPSST embeds the complete benefits of constraint association among pixels and superpixel edge data for accurate determination of the nuclei and cytoplasmic boundaries so as to ensure efficient differentiation of the healthy and unhealthy cancer cells. Finally, the pixel-level forecasting potential of Conditional Random Fields is included for enhancing the degree of semantic-based segmentation accuracy to a predominant level. The experimental evaluated results of the proposed IBGC-CRF-SPSST aim to produce an accuracy of 99.78%, a mean processing time of 2.18sec, a precision of 96%, a sensitivity of 98.92%, and a specificity of 99.32% value which is determined to be excellent and on par with the existing detection techniques used for investigating cervical cancer.

The paper presents a low-cost and LiDAR-free approach to efficiently detect 3D objects from stereo camera images, towards autonomous driving applications. It is first proposed to exploit the simple linear iterative clustering algorithm to segment stereo images into superpixel feature maps. The segmented superpixel maps are then used to estimate a depth map. By utilizing the depth map and stereo images, a 3D point cloud can be generated; and the 3D data is considered as pseudo-LiDAR representation as it is similar to measurements collected by a LiDAR sensor. The generated pseudo-LiDAR point cloud can ultimately be fed into any the state-of-the-art LiDAR based 3D object detection techniques to localize objects. By doing this, the proposed approach can effectively detect 3D objects by only employing low-cost stereo cameras, which can save tens of thousands of dollars on LiDAR costs from the existing LiDAR based methods. Effectiveness of the proposed algorithm was evaluated in the real-world KITTI dataset where the obtained results are about 1.33% better than those obtained by the benchmarking pseudo-LiDAR++ method (You et al. 2020). [ABSTRACT FROM AUTHOR]

Copyright of Journal of Signal Processing is the property of Journal of Signal Processing 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 order to solve the problem of noise sensitivity and low precision in image segmentation, a new image segmentation method based on super-pixel with neighborhood constrained and multi-level FCM clustering is proposed. Firstly, an improved SLIC algorithm of FCM is designed based on the local pixel region of the image to get the refined super-pixel. Then, the improved FCM clustering algorithm is combined with the spatial relationship of neighborhood super-pixel to mark the super-pixel categories. In order to verify the effectiveness of the algorithm, the artificial synthetic image with noise and natural image without noise are used for comparison experiments. The experimental result show the algorithm proposed in this paper can not only suppress the noise, but also improve the processing accuracy. [ABSTRACT FROM AUTHOR]

The process of intermittent leather inspection is being predominantly carried out with the support of human intervention based on homogenous distribution of colors. However, results of the observations between one experts to another expert may be different in opinion. Therefore, to emphasis some sort of supporting hand to the experts while taking decision, the authors have introduced an algorithm based on Image Score Pattern to distinguish between defect versus non-defect intermittent leather images. About 32 features generated from Gray Level Co-occurrence Matrix, Simple Linear Iterative Clustering and Minimum Spanning Tree Clustering from the training and testing datasets of about 1132 and 404 generated. The results of the classifier Support Vector Machine has confirmed the accuracy of 84% for the proposed Image Score Pattern method for these datasets. Similarly, other performance measures such as Precision, Recall, F1-Score, Specificity and Error Rate are also confirming that proposed method is performing in aligning of intermittent leather. [ABSTRACT FROM AUTHOR]

Logged forests cover four million square kilometers of the tropics, capturing carbon more rapidly than temperate forests and harboring rich biodiversity. Restoring these forests is essential to help avoid the worst impacts of climate change. Yet monitoring tropical forest recovery is challenging. We track the abundance of early-successional species in a forest restoration concession in Indonesia. If the species are carefully chosen, they can be used as an indicator of restoration progress. We present SLIC-UAV, a new pipeline for processing Unoccupied Aerial Vehicle (UAV) imagery using simple linear iterative clustering (SLIC)to map early-successional species in tropical forests. The pipeline comprises: (a) a field verified approach for manually labeling species; (b) automatic segmentation of imagery into “superpixels” and (c) machine learning classification of species based on both spectral and textural features. Creating superpixels massively reduces the dataset's dimensionality and enables the use of textural features, which improve classification accuracy. In addition, this approach is flexible with regards to the spatial distribution of training data. This allowed us to be flexible in the field and collect high-quality training data with the help of local experts. The accuracy ranged from 74.3% for a four-species classification task to 91.7% when focusing only on the key early-succesional species. We then extended these models across 100 hectares of forest, mapping species dominance and forest condition across the entire restoration project.

• The proposed work introduces a novel approach, termed Adaptive Histological Component Segmentation, which amalgamates GrabCut, Panoptic, and Simple Linear Iterative Clustering (SLIC) segmentation techniques. • This innovative method provides a comprehensive solution for accurate histopathologic image analysis, addressing limitations observed in existing models. • The model ensures dynamic hyperparameter optimization during training through the integration of SurroSec Optimizer, Epicurve Search, and PyramidalNetBlock. • A distinctive feature involves the special incorporation of Second-Order Methods with SurroSec Optimizer, further enhancing parameter exploration. Deep learning approaches have greatly improved the abilities in the field of histopathologic cancer diagnosis. To improve the precision and effectiveness of cancer diagnosis, this work proposes a complete technique called PathoNet, which combines state-of-the-art segmentation methodologies and optimization strategies. Using a combination of GrabCut, Panoptic, and Simple Linear Iterative Clustering (SLIC), the suggested model makes use of Adaptive Histological Component Segmentation. This multi-step procedure improves the recognition of structural and cellular elements in medical imaging, laying a solid basis for further examination. A novel PyramidalNetBlock architecture for adaptive hyper parameter optimization is also introduced by PathoNet, enhanced by an Epicurve Search – PyramidalSequentialBlock (PSB) model. Throughout the training, the Epicurve Search algorithm dynamically modifies important hyperparameters such as learning rates and epochs, facilitating efficient convergence and enhanced model generalization. Furthermore, parameter space exploration is further refined by the integration of SurroSec Optimizer, which is a combination of Surrogate Optimization and Second-Order Methods. A detailed performance investigation shows that the suggested model achieves state-of-the-art outcomes. PathoNet demonstrates its superiority with a testing accuracy of 98% through ablation tests and comparisons with current models. [ABSTRACT FROM AUTHOR]

Potholes are one of the most common forms of road damage, which can severely affect driving comfort, road safety, and vehicle condition. Pothole detection is typically performed by either structural engineers or certified inspectors. However, this task is not only hazardous for the personnel but also extremely time consuming. This article presents an efficient pothole detection algorithm based on road disparity map estimation and segmentation. We first incorporate the stereo rig roll angle into shifting distance calculation to generalize perspective transformation. The road disparities are then efficiently estimated using semiglobal matching. A disparity map transformation algorithm is then performed to better distinguish the damaged road areas. Subsequently, we utilize simple linear iterative clustering to group the transformed disparities into a collection of superpixels. The potholes are finally detected by finding the superpixels, whose intensities are lower than an adaptively determined threshold. The proposed algorithm is implemented on an NVIDIA RTX 2080 Ti GPU in CUDA. The experimental results demonstrate that our proposed road pothole detection algorithm achieves state-of-the-art accuracy and efficiency. [ABSTRACT FROM AUTHOR]

An efficient and accurate identification of damaged buildings after earthquakes is critical for ensuring a quick response and efficient rescue operations. Considering the time pressure during disaster emergency response and the convenience of practical application, a new approach for identifying areas with damaged buildings is proposed in this study. The approach is validated on high-resolution images from areas impacted by the Haiti earthquake. The approach consists of the following steps. (i), the simple linear iterative clustering method is improved to segment the images into high-quality superpixels by combining both color and texture information; (ii) the characteristics of the damage in the area within the cluster and the difference between pre- and post-earthquake images are obtained at superpixel level using the Sobel gradient; and (iii) local indicators from the spatial association analysis are used to extract the result of the gradient clustering using the synthetic- damage index calculated by an improved relief algorithm; and (iv) vegetation and shadows are masked out to identify the damaged buildings. This framework achieved an overall accuracy of ~90% in terms of visual interpretation, with precision and recall of ~85% and ~90%, respectively. Inaccuracies mainly occur around the boundaries of the damaged building regions. It is evaluated that the proposed framework is more convenient compared to other supervised and unsupervised methods. The successful application in different scenes demonstrates that the proposed framework has the ability to rapidly and accurately identify regions with damaged buildings, which is beneficial for post-disaster emergency assessment.

With the development of bionic computer vision for images processing, researchers have easily obtained high-resolution zoom sensing images. The development of drones equipped with high-definition cameras has greatly increased the sample size and image segmentation and target detection are important links during the process of image information. As biomimetic remote sensing images are usually prone to blur distortion and distortion in the imaging, transmission and processing stages, this paper improves the vertical grid number of the YOLO algorithm. Firstly, the light and shade of a high-resolution zoom sensing image were abstracted, and the grey-level cooccurrence matrix extracted feature parameters to quantitatively describe the texture characteristics of the zoom sensing image. The Simple Linear Iterative Clustering (SLIC) superpixel segmentation method was used to achieve the segmentation of light/dark scenes, and the saliency area was obtained. Secondly, a high-resolution zoom sensing image model for segmenting light and dark scenes was established to made the dataset meet the recognition standard. Due to the refraction of the light passing through the lens and other factors, the difference of the contour boundary light and dark value between the target pixel and the background pixel would make it difficult to detect the target, and the pixels of the main part of the separated image would be sharper for edge detection. Thirdly, a YOLO algorithm with an improved vertical grid number was proposed to detect the target in real time on the processed superpixel image array. The adjusted aspect ratio of the target in the remote sensing image modified the number of vertical grids in the YOLO network structure by using 20 convolutional layers and five maximum aggregation layers, which was more accurately adapted to “short and coarse” of the identified object in the information density. Finally, through comparison with the improved algorithm and other mainstream algorithms in different environments, the test results on the aid dataset showed that in the target detection of high spatial resolution zoom sensing images, the algorithm in this paper showed higher accuracy than the YOLO algorithm and had real-time performance and detection accuracy.

Non-uniform temperature distributions in ovens affect the quality of baked goods and raise concerns regarding food safety. Traditional research on oven performance focuses on the heating mechanisms in simulated ovens and does not involve quantitative analysis of baked goods. This study proposes a model for calculating the uniformity of baked goods based on image processing technology, to quantitatively assess the distribution uniformity of different baked states and digitally express the internal temperature field distribution in the oven. First, the image of the baked goods is captured using a digital camera. Then, it is preprocessed to obtain an image containing only the region showing the baked goods. Subsequently, the simple linear iterative clustering segmentation algorithm is employed to extract the baked states. Finally, a meshing model is applied to calculate the distribution variance of each baked state, and the evaluation index describing the uniformity of the baked goods image is obtained by normalizing the variance in the distribution. The simple linear iterative clustering segmentation algorithm expresses the color features of acquired baked goods images in the form of superpixels. By determining the distribution and proportion of different baked states, the proposed method can qualitatively and quantitatively reflect the spatial distribution of the temperature fields inside the oven corresponding to the baked goods image. This provides a strong basis for further evaluation of the heat distribution field inside the oven.

Because the simple linear iterative clustering (SLIC) algorithm is not ideal for the edge segmentation of synthetic aperture radar (SAR) images containing speckle noise, a superpixel segmentation algorithm of SAR image based on coefficient of variation CCV) is proposed. The algorithm first performs anisotropic Gaussian smoothing preprocessing on the SAR image, so that the image speckle are smoothed while the edge information is not destroyed. Secondly, CV is used to estimate the speckle edge information, making it easier to distinguish the homogenous area and the edge area of the image. Finally, the SLIC algorithm with edge information is used for clustering to generate superpixel. Experimental results show that the recall rate of this algorithm is increased by at least 5% compared with the three classic superpixel algorithms under SAR image segmentation, and when the number of superpixel is greater than 400, the under-segmentation error rate is reduced by 2% . This algorithm improves the accuracy of SAR image superpixel segmentation, and its edges are more suitable to the real edges of the image. [ABSTRACT FROM AUTHOR]

A local color image watermarking scheme using adaptive segmentation-based feature extraction (ASFE) and singular value decomposition-based spread transform dither modulation (S-STDM) is proposed in this paper. The proposed ASFE can adaptively extract feature regions from blocks segmented by the simple linear iterative clustering. In addition, the stationary wavelet transform is employed to decompose each of the extracted feature regions because of its shift invariance. Consequently, the novel S-STDM watermarking method is proposed, where we employ singular value decomposition to calculate the approximation coefficients and then select the generated diagonal elements from the decomposed diagonal matrix for watermark message embedding. The experimental results show that the proposed scheme is superior to the existing schemes under various attacks. [ABSTRACT FROM AUTHOR]

Superpixel generation finds wide variety of applications in the field of image processing, particularly brain tumour detection, human body pose estimation, person re-identification as a pre-processing step. In this paper, we present a novel superpixel segmentation approach through integration of curvelet transform and conventional Simple Linear Iterative Clustering (SLIC) for image and video. The proposed algorithm follows a two-step framework, clustering in curvelet and spatial domain separately. It performs conventional Simple Linear Iterative clustering on curvelet coefficients obtained at different decomposition levels of R, G, B components as well as directly on R, G, B components to get initial boundaries of superpixels. We obtain final boundaries of superpixels by taking the high probable boundaries from the initial formed boundaries. By incorporation of curvelets in five different scales the proposed method is capable of generating superpixels with high boundary adherence even in the presence of background change, object motion and noise. Superpixels generated by the proposed method are homogeneous in regions of complex texture and weak boundaries. The method has been tested on different images taken from Berkeley segmentation dataset and frames of several other videos. The algorithm under study is evaluated in terms of ten evaluation parameters: boundary recall, boundary precision, quality percentage, detection percentage, accuracy, Jaccard index, specificity, figure of merit, structural content, achievable segmentation accuracy. The results are tabulated, shown graphically and discussed in detail. The critical analysis of results show sound performance of the proposed method over other state-of- art methods. [ABSTRACT FROM AUTHOR]

Image splicing/compositing is common content tampering operation. In this work, we devote to improve the detection accuracy of the splicing/compositing attack for image, and propose an effective image splicing localization method based on the noise distribution characteristic in image. Firstly, the test image is divided into non-overlapping blocks by using an improved simple linear iterative clustering (SLIC) algorithm. Then block-wise local noise level estimation and noise distribution characteristic estimation are performed to generate distinguishing features. Utilizing the fact that image regions from different sources tend to have larger inter-class difference, the fuzzy c-means clustering is used to identify spliced regions. Compared to existing noise-based image splicing detection methods, experimental results on different datasets have shown that the proposed method has superior performance, especially when the noise difference between the spliced region and the original region is small. Moreover, the proposed method is robust for content-preserving manipulations. [ABSTRACT FROM AUTHOR]

Obtaining accurate global motion is a crucial step for video stabilization. This paper proposes a robust and simple method to implement global motion estimation. We don’t extend the framework of 2D video stabilization but add a “plug and play” module to motion estimation based on feature points. Firstly, simple linear iterative clustering (SLIC) pre-segmentation is used to obtain superpixels of the video frame, clustering is performed according to the superpixel centroid motion vector and cluster center with large value is eliminated. Secondly, in order to obtain accurate global motion estimation, an improved K-means clustering is proposed. We match the feature points of the remaining superpixels between two adjacent frames, establish a feature points’ motion vector space, and use improved K-means clustering for clustering. Finally, the richest cluster is being retained, and the global motion is obtained by homography transformation. Our proposed method has been verified on different types of videos and has efficient performance than traditional approaches. The stabilization video has an average improvement of 0.24 in the structural similarity index than the original video and 0.1 higher than the traditional method.

The simple linear iterative clustering (SLIC) is the most popular superpixel segmentation method for its simplicity and effectiveness. In this Letter, we propose an edge attention‐based geodesic distance, which can be applied to the SLIC framework for polarimetric synthetic aperture radar image superpixel segmentation. Image edges are especially considered to generate superpixels with better boundary adherence property, while the computing burden does not increase. Specifically, the authors first detect image edges, then fuse the edge map and polarimetric dissimilarity, and finally define the geodesic distance based on the fused results. Experiments performed on real scene images demonstrate the superiority of the proposed distance in both qualitative and quantitative ways. [ABSTRACT FROM AUTHOR]

This study investigates the suitability of objectand pixel-based approaches for extraction of hazelnut trees from high resolution digital orthophoto maps. For object-based approach, simple linear iterative clustering (SLIC) method was employed to segment image pixels into homogeneous regions. Features spanning spectral, spatial and textural domains were extracted from each segment then classification was performed by employing support vector machine (SVM) classifier. For pixel-based approach, the spectral reflectance information from all four bands were used as features and applied maximum likelihood (ML) classifier for classification of each pixel into hazelnut and other tree species classes. An areabased approach was used to evaluate the performance of the proposed method. The experiments showed that overall classification accuracy for objectǦbased method was superior to the pixel-based method. Using object-based approach the overall accuracy obtained was 86% while pixel-based approach scored 76%. [ABSTRACT FROM AUTHOR]

Reversible image watermarking schemes are used to protect ownership and copyrights of digital images. This paper proposes a novel reversible image watermarking scheme based on adaptive image interpolation, segmentation and additive prediction error expansion (PEE). Proposed interpolation comprises of weighted average of neighboring pixels by allocating higher and lower weights to less and more distant neighboring pixel values respectively. The proposed adaptive image interpolation focuses on detection of edges thus minimizing artifacts imposed by interpolation. The idea of embedding varying amount of watermark bits in different image segments has been explored. Simple linear iterative clustering (SLIC) based image segmentation is performed to separate very sharp, sharp, smooth and very smooth regions in image. Higher number of watermark bits are embedded in sharp regions by using additive prediction error expansion embedding technique. Simulations of proposed and existing techniques were performed on different images and compared using embedding capacity (EC), peak signal to noise ratio (PSNR), computational efficiency, image quality, mean square error (MSE), normalized cross correlation (NCC) and structural similarity index (SSIM). The experimental results show that proposed scheme achieves better results in terms of EC, PSNR, computational efficiency, image quality, MSE, NCC and SSIM as compared to existing techniques. [ABSTRACT FROM AUTHOR]

Non-uniform gray distribution and blurred edges often result in bias during the superpixel segmentation of medical images of magnetic resonance imaging (MRI). To this end, we propose a novel superpixel segmentation algorithm by integrating texture features and improved simple linear iterative clustering (SLIC). First, a 3D histogram reconstruction model is used to reconstruct the input image, which is further enhanced by gamma transformation. Next, the local tri-directional pattern descriptor is used to extract texture features of the image; this is followed by an improved SLIC superpixel segmentation. Finally, a novel clustering-center updating rule is proposed, using pixels with gray difference with original clustering centers smaller than a predefined threshold. The experiments on the Whole Brain Atlas (WBA) image database showed that, compared to existing state-of-the-art methods, our superpixel segmentation algorithm generated significantly more uniform superpixels, and demonstrated the performance accuracy of the superpixel segmentation in both fuzzy boundaries and fuzzy regions.

In the field of machine vision defect detection for a micro workpiece, it is very important to make the neural network realize the integrity of the mask in analyte segmentation regions. In the process of the recognition of small workpieces, fatal defects are always contained in borderline areas that are difficult to demarcate. The non-maximum suppression (NMS) of intersection over union (IOU) will lose crucial texture information especially in the clutter and occlusion detection areas. In this paper, simple linear iterative clustering (SLIC) is used to augment the mask as well as calibrate the score of the mask. We propose an SLIC head of object instance segmentation in proposal regions (Mask R-CNN) containing a network block to learn the quality of the predict masks. It is found that parallel K-means in the limited region mechanism in the SLIC head improved the confidence of the mask score, in the context of our workpiece. A continuous fine-tune mechanism was utilized to continuously improve the model robustness in a large-scale production line. We established a detection system, which included an optical fiber locator, telecentric lens system, matrix stereoscopic light, a rotating platform, and a neural network with an SLIC head. The accuracy of defect detection is effectively improved for micro workpieces with clutter and borderline areas.

Digital images assume a vital part both in day by day life applications, for example, satellite TV, computed tomography, magnetic resonance imaging and additionally in ranges of research and innovation, for example, cosmology and geographical information systems. An expansive segment of computerized image preparing incorporates image restoration. Image restoration is a technique for removal or decrease of corruption that are caused amid the image catching. Corruption originates from obscuring as well as commotion due to the electronic and photometric sources. Obscuring is the type of data transfer capacity decrease of images caused by flawed image development process, for example, relative movement amongst camera and unique scene or by an optical framework that is out of core interest. Image Denoising is an important pre-processing task before further processing of the image like segmentation, feature extraction, texture analysis, etc. which removes the noise while retaining the edges and other detailed features as much as possible. This noise gets introduced during acquisition, transmission & reception and storage & retrieval processes. This paper presents a novel pre-processing algorithm which is named as Profuse Clustering Technique (PCT) based on the super pixel clustering. K-Means clustering, Simple Linear Iterative Clustering, Fusing Optimization algorithms are involved in this proposed Profuse Clustering Technique and is further used for denoising the Lung Cancer images to get the more accurate result in the decision making process. [ABSTRACT FROM AUTHOR]

In looking to improve the detection performance of the keypoint-based method involving smooth tampered regions, there are three problems to be addressed, namely the nonuniform distribution of the keypoints, the discriminative power of low contrast keypoints, and the high computational cost of clustering. In this study, the classical implementation framework of the keypoint-based method is improved by introducing new techniques and algorithms in order to overcome these problems. First, to acquire uniformly distributed keypoints in the test image, we propose a new solution of selecting the keypoints by region instead of contrast. To this end, we first separate the keypoint detection and selection processes. After obtaining all discernible keypoints, we adapt the non-maximum value suppression algorithm to select keypoints by combining the contrast and density of each keypoint. Second, we apply the opponent scale-invariant feature transform descriptor to enhance the discriminative power of keypoints by adding color information. Finally, to alleviate the computational cost of clustering, we optimize the J-Linkage algorithm by altering the method of computing initial clusters and affine transformation hypotheses. For this purpose, we propose the matched pair grouping algorithm that can obtain a smaller number of initial clusters by utilizing the correspondence between the superpixels in the original and duplicated regions. Experiments performed on three representative datasets confirm that the proposed method can significantly improve the detection performance in smooth tampered regions, and considerably reduce the clustering time in the case of a mass of matched pairs, compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper presents a non-interactive building detection approach employing binary bag-of-features (BBOF), namely, extracting building roof contours in remote sensing images automatically, rapidly and accurately. The proposed method includes two major stages, i.e., building area detection and building contours extraction. In the first stage, it contains three modules. i.e., oversegmentation, intersection point classification, building area detection. Firstly, the orthophoto is over-segmented by the Simple Linear Iterative Clustering (SLIC) superpixel segmentation method, and the intersection points is obtained. Secondly, the oriented FAST and rotated BRIEF (ORB) descriptors are generated in LAB colour space from the patches that centred on the intersection points, and the BBOF classifier is adopted to classify the intersection points into two categories. Thirdly, the area that contains of the building roof are detected through reserving the regions around the intersection points in inner parts of building roof, and eliminating the regions around the intersection points in non-building roof. At last, we can roughly generate the building area. For the second stage, it is similar to the first one while the main difference is that its classifier has three categories. Finally, we provide an evaluation between two different classifiers, including ORB+BBOF and SURF+BOF. This evaluation is conducted on orthophotos with different roof colours, texture, shape, size and orientation. The proposed approach presents several advantages in terms of scalability, suitability and simplicity with respect to the existing methods. [ABSTRACT FROM AUTHOR]

The success of cluster analysis for revealing natural grouping in a dataset depends heavily on the chosen dissimilarity measure. Recently, several attempts have been made to replace the popular Euclidean distance measure for dissimilarity with divergences that are known to disobey triangular inequality. In this Letter, a representative partitioning based superpixel algorithm called Simple Linear Iterative Clustering (SLIC) is experimented with a divergence measure. In particular, the Jeffery divergence is employed for dissimilarity computation between colour‐image plane space vectors while performing cluster assignment. Despite being a non‐metric, the Jeffery divergence based SLIC has shown better boundary adherence performance on BSDS500 dataset as compared to the conventional SLIC algorithm. [ABSTRACT FROM AUTHOR]

The simple linear iterative clustering (SLIC) method is a recently proposed popular superpixel algorithm. However, this method may generate bad superpixels for synthetic aperture radar (SAR) images due to effects of speckle and the large dynamic range of pixel intensity. In this paper, an improved SLIC algorithm for SAR images is proposed. This algorithm exploits the likelihood information of SAR image pixel clusters. Specifically, a local clustering scheme combining intensity similarity with spatial proximity is proposed. Additionally, for post-processing, a local edge-evolving scheme that combines spatial context and likelihood information is introduced as an alternative to the connected components algorithm. To estimate the likelihood information of SAR image clusters, we incorporated a generalized gamma distribution (GÃD). Finally, the superiority of the proposed algorithm was validated using both simulated and real-world SAR images. [ABSTRACT FROM AUTHOR]

• Online analysis of particulate feed in mineral processing is not well established. • Segmentation of images of densely packed particles is a challenging task. • Here, particle boundaries were explicitly included in image segmentation. • The results obtained with a U-net neural network were promising. • Segmentation could be further improved with superpixelation of images. Particle size distributions in ore feed systems, as well as the identification of particles in these feed systems can provide important information in the advanced control of unit operations in mineral processing, such as crushing and grinding circuits. Image analysis has long been considered a promising approach to achieve this, as it is an inexpensive, unobtrusive means of acquiring information rich measurements. It typically requires segmentation of images in order to identify individual particles. This is a challenging task to accomplish reliably, as variable lighting, fines adhering to larger particles or contiguous particles, as well as variable particle sizes and shapes can all compromise the accuracy of traditional algorithms. Image segmentation with deep learning methods have recently been investigated to surmount these difficulties. In this investigation, U-net and U-net with superpixel preprocessing with simple linear iterative clustering (SLIC) are proposed and compared with a traditional watershed algorithm. The U-net approaches were markedly more reliable than the watershed algorithm. In addition, preprocessing of the images with SLIC resulted in further improvement of the results. [ABSTRACT FROM AUTHOR]

For complex images, interactive image segmentation can achieve better segmentation performance than other approaches. However, many classical interactive segmentation methods are sensitive to the locations and number of seed pixels. We introduce a seed extraction method to address this issue. First, we propose a robust seed measure to select and mark the seed pixels that cover the whole image. We use the center pixel of each superpixel as a seed. Then, each center pixel is labeled by our seed measure. Second, we propose a relabeling method for addressing isolated seeds. The extracted seeds can be used to locate the initial object area and can serve as the inputs of other interactive segmentation methods to reduce their dependence on user interaction. Extensive experiments on the Berkeley, GrabCut, and MSRA1000 datasets demonstrate the effectiveness of our seed extraction method. [ABSTRACT FROM AUTHOR]

As an active forensic technology, perceptual image hash has important application in image content authenticity detection and integrity authentication. In this paper, we propose a hybrid-feature-based perceptual image hash method that can be used for image tampering detection and tampering localization. In the proposed method, we use the color features of image as global features, use point-based features and block-based features as local features, and combine with the structural features to generate intermediate hash code. Then we encrypt and randomize to generate the final hash code. Using this hash code, we present a coarse-to-fine grained forensics method for image tampering detection. The proposed method can realize object-level tampering localization. Abundant experimental results show that the proposed method is sensitive to content changes caused by malicious attacks, and the tampering localization precision achieves pixel level, and it is robust to a wide range of geometric distortions and content-preserving manipulations. Compared with the state-of-the-art schemes, the proposed scheme yields superior performance. [ABSTRACT FROM AUTHOR]

Obtaining accurate global motion is a crucial step for video stabilization. This paper proposes a robust and simple method to implement global motion estimation. We don't extend the framework of 2D video stabilization but add a "plug and play" module to motion estimation based on feature points. Firstly, simple linear iterative clustering (SLIC) pre-segmentation is used to obtain superpixels of the video frame, clustering is performed according to the superpixel centroid motion vector and cluster center with large value is eliminated. Secondly, in order to obtain accurate global motion estimation, an improved K-means clustering is proposed. We match the feature points of the remaining superpixels between two adjacent frames, establish a feature points' motion vector space, and use improved K-means clustering for clustering. Finally, the richest cluster is being retained, and the global motion is obtained by homography transformation. Our proposed method has been verified on different types of videos and has efficient performance than traditional approaches. The stabilization video has an average improvement of 0.24 in the structural similarity index than the original video and 0.1 higher than the traditional method. [ABSTRACT FROM AUTHOR]

• Computer vision based leaf disease segmentation and classification. • Jatropha Curcas L. and Pongamia Pinnata L. biofuel plants were adopted. • Neural network and superpixel clustering was used for segmentation. • Color, texture, and shape features were extracted using different algorithms. • Seven machine learning approaches were used for the purpose of classification. Several efforts have been made in finding alternate sources of energy. The production of bio-fuel from the extracts of plants like Jatropha Curcas L. and Pongamia Pinnata L. is most favored among all. But, due to certain biotic factors, the growth of these plants get affected, therefore reducing the overall production. To formulate the demand and automate the disease diagnosis system a Computer vision methodology is proposed in this work. For disease region segmentation, a Hybrid Neural Network incorporated with Superpixel clustering is proposed. Color, shape, and texture features are evaluated using different algorithms. Finally, seven different Machine Learning techniques were used to classify the images among three categories. Segmentation results with average Specificity = 0.9534, 0.9795, Sensitivity = 0.9637, 0.9805 and average Classification accuracy = 0.9857 ± 0.0285, 0.9095 ± 0.0688 and 0.9607 ± 0.0256 for both the plants when evaluated separately proved the supremacy of the proposed work. [ABSTRACT FROM AUTHOR]

Non-uniform gray distribution and blurred edges often result in bias during the superpixel segmentation of medical images of magnetic resonance imaging (MRI). To this end, we propose a novel superpixel segmentation algorithm by integrating texture features and improved simple linear iterative clustering (SLIC). First, a 3D histogram reconstruction model is used to reconstruct the input image, which is further enhanced by gamma transformation. Next, the local tri-directional pattern descriptor is used to extract texture features of the image; this is followed by an improved SLIC superpixel segmentation. Finally, a novel clustering-center updating rule is proposed, using pixels with gray difference with original clustering centers smaller than a predefined threshold. The experiments on the Whole Brain Atlas (WBA) image database showed that, compared to existing state-of-the-art methods, our superpixel segmentation algorithm generated significantly more uniform superpixels, and demonstrated the performance accuracy of the superpixel segmentation in both fuzzy boundaries and fuzzy regions. [ABSTRACT FROM AUTHOR]

Sonar is one of the most important tools for underwater object detection and submarine topography reconstruction. To classify sonar images automatically and accurately is essential for the navigation and path planning of autonomous underwater vehicles (AUV). However, for the intensity inhomogeneity and speckle noise in sonar images, it is difficult to obtain segmentation results of high accurate rate. To address these issues, in this paper, we advocate a segmentation method incorporating simple linear iterative clustering (SLIC) and adaptive intensity constraint into Markov random field (MRF), to segment sonar images with intensity inhomogeneity into the object highlight, the object shadow and the background areas. The main procedures of the proposed work are as follows: first, SLIC is used to separate sonar images into homogeneous super pixels, and second the homogeneity patches, with a novel intensity constraint strategy, is utilized to optimize the segmentation result of MRF at each iteration. Experimental results reveal that the proposed method performs well and fast on real sonar images which have intensity inhomogeneity problem. [ABSTRACT FROM AUTHOR]

In the field of machine vision defect detection for a micro workpiece, it is very important to make the neural network realize the integrity of the mask in analyte segmentation regions. In the process of the recognition of small workpieces, fatal defects are always contained in borderline areas that are difficult to demarcate. The non-maximum suppression (NMS) of intersection over union (IOU) will lose crucial texture information especially in the clutter and occlusion detection areas. In this paper, simple linear iterative clustering (SLIC) is used to augment the mask as well as calibrate the score of the mask. We propose an SLIC head of object instance segmentation in proposal regions (Mask R-CNN) containing a network block to learn the quality of the predict masks. It is found that parallel K-means in the limited region mechanism in the SLIC head improved the confidence of the mask score, in the context of our workpiece. A continuous fine-tune mechanism was utilized to continuously improve the model robustness in a large-scale production line. We established a detection system, which included an optical fiber locator, telecentric lens system, matrix stereoscopic light, a rotating platform, and a neural network with an SLIC head. The accuracy of defect detection is effectively improved for micro workpieces with clutter and borderline areas. [ABSTRACT FROM AUTHOR]