Video segmentation has become a fundamental of various multimedia applications. Spatiotemporal coherence is important for video segmentation. In this study, to balance the spatiotemporal coherence in scenes with deformation or large motion, the authors propose a novel segmentation scheme based on the absorbing Markov chain (AMC) model named directed graph segmentation based on AMC. In their study, they first generate primary proposals per frame. Then, they train weight models by using a part of primary proposals with their features and feature scores. Next, they construct a directed AMC graph, in which states are the generated primary proposals and edge weights are decided by trained weight models. They subsequently perform the first proposal selection per frame by thresholding the modified absorbed time. Afterwards, they design a reselection algorithm to filter the selected proposals and ensure the proposals, which are the most likely to be the motion object in each frame, to be selected as candidates. Finally, they employ the graph-cuts based optimisation algorithm to generate refined per pixel segmentation by using object and background models built by candidate proposals under the concept of Gaussian mixture models. Experimental results demonstrate that the proposed scheme shows competitive performance compared with advanced algorithms.

This study introduces an action descriptor that has the ability to perform human action recognition efficiently for one and two person(s). The authors’ proposed descriptor computes information like motion, spatial–temporal, diversion with respect to the centroid, critical point and keypoint detection, whereas the existing approaches lack to address this information efficiently. Action descriptors are developed from signature-based optical flow, signature-based corner points and binary robust invariant scalable keypoints. These action descriptors are applied to silhouette and silhouette's skeleton frames. These aforementioned action descriptors lead to developing the concatenated action descriptor (CAD). In order to develop action descriptors, the reference video frame plays an important role. Weizmann (one person) and both clean and noise versions of SBU Kinect Interaction (two persons) datasets are used for the evaluation of their proposed descriptors. On the other hand, classifications are performed by using support vector machine. Experimental results demonstrate that CAD not only outperforms among the entire proposed descriptors, but also provides better performance as compared to state-of-the-art approaches.

Indoor positioning techniques have become very important in recent years. Due to the wide deployment of surveillance cameras, it has become feasible to use the videos for indoor positioning. The success of using this approach can also reduce the load of security persons of watching the monitors all the time. In this study, the authors propose a vision-based indoor positioning system. The proposed method uses a frame processing technique and applies the Gaussian mixture learning for video background model. The foreground object can be extracted by using the background subtraction. Based on the foreground object, the objects can be tracked and used in the direct linear transform, and generate a bird's-eye map with camera information. A real-time demonstration has been also provided. It shows the tracing of the moving objects and the bird's-eye view.

Block-matching and three-dimensional filtering (BM3D) is generally considered as a milestone for its outstanding performance in the area of image denoising. However, it still suffers from the loss of image detail due to the utilisation of hard thresholding on transform domain during the phase of the basic estimate. In the frequency domain, a large amount of image detail information is in high frequency, which tends to be mixed with noise. Since its low amplitude is below the threshold, some image detail is filtered out with the noise. To retain more details, this study proposes an improved BM3D. It adopts an adaptable threshold with the core of Gaussian function during hard thresholding, which can filter out more noise while retaining more high-frequency information. When grouping, the normalised angular distance is taken as a measure of similarity to relieve the interference of noise further and achieve a higher peak signal-to-noise ratio (PSNR). The experimental results show that under the background of Gaussian noise with standard deviation of 20–60, the PSNR of denoised images (with a large amount of detail), applied with the authors’ improved algorithm, can be improved by compared with original BM3D.

Medical imaging systems contribute much towards effective decision-making by the physicians, which is highly essential in the day-to-day life of humans. In this study, Taylor–Krill herd (KH)-based support vector machine (SVM) is proposed for medical image denoising. The Taylor–KH-based SVM is the integration of Taylor series in KH optimisation algorithm, which is used for tuning the optimal weights of the SVM classifier. The efficiency of KH is due to two global and two local optimisers, and the adaptive operators ensure the adaptive nature of KH. Above all, KH never uses the derivative information as it employs the stochastic search and thereby, reduces the complexity of the algorithm. The proposed method tunes the hyperplane parameters of SVM optimally so that the optimal identification of the noisy pixels in the image is ensured and replaced with adaptive weights. The proposed method is analysed based on the metrics, such as peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and the comparative analysis is done with existing methods for showing the effectiveness of the proposed method. The simulation result shows that the proposed method acquired a PSNR of 30.36 dB and SSIM of 0.89, respectively.

Humans often use faces to recognise and identify individuals. Face recognition is one of the important tasks carried out by forensic examiners manually during their investigation, when there is an evidence image/video available from a crime scene. There is a growing demand for face recognition from unconstrained images, which is valuable for criminal investigators in identifying the victims. When an input face image is given to the proposed system, it filters from large scale face dataset to find the top-k similar faces. Deep convolutional neural network approach is employed to extract important features present in the input face image and improved grey wolf optimisation approach is proposed to select optimal features from the extracted features. It is then preceded by a soft biometric-based face matcher that helps in retrieving exact face image from the top-k similar faces matched using approximate nearest neighbour. The performance of the proposed system is evaluated using LFW, CASIA, Multi-pie and Color-Feret datasets. The proposed system addresses the challenge of searching face images from a large collection of unconstrained images by incorporating feature retrieval using DCNN and IGWO with soft biometric face matcher in cascaded framework which improves accuracy and reduces computation and retrieval time.

Image forgery detection and localisation is one of the principal problems in digital forensics. Copy–paste forgery in digital images is a type of forgery in which an image region is copied and pasted at another location within the same image. In this work, the authors propose a methodology to detect and localise copy-pasted regions in images based on scale-invariant feature transform (SIFT). Existing copy-paste forgery detection in images using SIFT and clustering techniques such as hierarchical agglomerative and density-based spatial clustering of applications with noise resulted many false pixel detections. They have introduced sensitivity-based clustering along with SIFT features to identify copy–pasted pixels and disregard the false pixels. Experimental evaluation on public image datasets MICC-F220, MICC-F2000 and MICC-F8 multi shows that the proposed method is showing improved performance in detecting and localising copy-paste forgeries in images than the existing works. Also the proposed work detects multiple copy–pasted regions in the images and is robust to attacks such as geometrical transformation of copied regions such as scaling and rotation.

Image filtering is a fundamental preprocessing step for accurate, robust computer vision applications such as image segmentation, object classification, and reconstruction. However, many convolutional neural network (CNN)-based methods tend to lose significant edge information in the output layer, and generate undesired artefacts in the feature extraction layers. This study presents a deep CNN model for edge-aware image filtering. The proposed network model consists of three sub-networks: (i) feature extraction, (ii) convolution artefact removal, and (iii) structure extraction networks. The proposed network model has an end-to-end trainable architecture that does not need any post-processing steps. Especially, the structure extraction network can successfully preserve significant edges. The proposed filter outperforms state-of-the-art denoising filters in terms of both objective and subjective measures, and can be used for various image enhancement and restoration problems such as edge-preserving smoothing, image denoising, deblurring, and deblocking.

The deep convolutional neural network (CNN) has recently attracted the researchers for classification of hyperspectral remote sensing images. The CNN mainly consists of convolution layer, pooling layer and fully connected layer. The pooling is a regularisation technique and improves the performance of CNN while reducing the computation time. Various pooling strategies have been developed in literature. This study shows the effect of pooling strategy on the performance of deep CNN for classification of hyperspectral remote sensing images. The authors have compared the performance of various pooling strategies such as max pooling, average pooling, stochastic pooling, rank-based average pooling and rank-based weighted pooling. The experiments were performed on three well-known hyperspectral remote sensing datasets: Indian Pines, University of Pavia and Kennedy Space Center. The proposed experimental results show that max pooling has produced better results for all the three considered datasets.

Image classification is one of the popular fields for researchers in computer vision. This study highlights the use of simple linear iterative clustering (SLIC) superpixel in combination with fast and automatically adjustable Gaussian radial basis function kernel-based fuzzy C-means (FAAGKFCM) for image segmentation along with the deep learning techniques. Bag-of-feature with speeded up robust feature along with deep features are used for classification of 101 classes of the image and 256 classes of the image from Caltech 101, Caltech 256 and MIT 67 image datasets. The combination of SLIC superpixel with FAAGKFCM image segmentation acts as the pre-processing step for image classification, which in turn provides a better result in the classification of images. This method has achieved an accuracy of 94% in Caltech 101 dataset, 85% in Caltech 256 dataset and 84% in MIT 67 dataset.

Breast cancer becomes a significant public health problem in the world. During the early detection of breast cancer, it is a very challenging task to classify accurately the benign–malignant patterns in digital mammograms. This study proposes a new fully automated computer-aided diagnosis (CAD) system for breast cancer diagnosis with high-accuracy and low-computational requirements. The expectation–maximisation algorithm is investigated to extract automatically the region of interests (ROIs) within mammograms. The standard shape, statistical, and textural features of ROIs are extracted and combined with multi-resolution and multi-orientation features derived from a new feature extraction technique based on wavelet-based contourlet transform. A hybrid feature selection approach based on combining the support vector machine recursive feature elimination with correlation bias reduction algorithm is proposed. Also, the authors investigate a new similarity-based learning algorithm, called Q, for benign–malignant classification. The proposed CAD system is applied to real clinical mammograms, and the experimental results demonstrate the superior performance of the proposed CAD system over other existing CAD systems in terms of accuracy 98.16%, sensitivity 98.63%, specificity 97.80%, and computational time 2.2 s. This reveals the effectiveness of the proposed CAD system in improving the accuracy of breast cancer diagnosis in real-time systems.

Magnetic resonance imaging (MRI) has emerged as the golden reference for cardiac examination. This modality allows the assessment of human cardiovascular morphology, functioning, and perfusion. Although a couple of challenging issues, such as the cardiac magnetic resonance (MR) image's features and the large variability of images among several patients, still influences the cardiac cavities’ segmentation and needs to be carried out. In this study, the authors have profoundly reviewed and fully compared semi-automated segmentation methods performed on cardiac cine-MR short-axis images for the evaluation of the left ventricular functions. However, the number of parameters handled by the synthesised works is limited if not null. For the sake of ensuring the highest coverage of the left ventricle parameters computing, they have introduced a parallel watershed-based approach to segment the left ventricular allowing hence the computation of six parameters (end-diastolic volume, end-systolic volume, ejection fraction, cardiac output, stroke volume, and left ventricular mass). An algorithm is associated with the main considered measurements. The experimental results that were obtained through studying 20 patients’ MRI data base demonstrate their approach's accuracy in estimating real values of the parameters’ set thanks to a faithful segmentation of the myocardium.

In this study, the authors advance a novel multiple images encryption algorithm using the coupled map lattices (CML) system and DNA encoding. The algorithm adopts a permutation-diffusion structure. First, the initial values and parameters of the CML system are determined by given values and SHA hash key of original images. Secondly, several plain images are grouped and permuted among groups. Next, different groups are combined into eight blocks of the same size, each of which is independently coded and scrambled. Thirdly, in the diffusion process, a DNA-level multiplication operation is redefined, and required key matrices are resulted from a small key connected with original images. Finally, dynamic DNA coding/decoding is adopted, and the coding and decoding rules are determined by original images. The evaluation of the simulation experiment shows that the proposed algorithm is safe and feasible, and has good encryption effect.

The -threshold image secret sharing (ISS) encodes a secret image into n shares. When k or more shares are obtained, the secret image can be decoded; however, less than k shares could decode none of the secret image. ISS primarily includes polynomial-based ISS and visual secret sharing (VSS). In this study, the authors find that the random elements in ISS can be used not only to hide information but also to obtain more features such as multiple decryptions and comprehensible share. They have established an application model of random elements that is suitable for both polynomial-based ISS and VSS. On the basis of the model, they have extended three algorithms to achieve information hiding, multiple decryptions and comprehensible share. Experiments indicate the effectiveness of these algorithms.

Otsu's method is one of the most well-known methods for automatic thresholding, which serves as an important algorithm category for image segmentation. However, it fails if the histogram is close to unimodal or has large intra-class variances. To alleviate this limitation, improved Otsu's methods such as the valley emphasis method and weighted object variances method have been proposed, which still yield non-optimal segmentation performance in some cases. In this study, a modified valley metric using second-order derivative is proposed to improve the Otsu's algorithm. Experiments are firstly conducted on five typical test images whose histograms are unimodal, multimodal or have large intra-class variances, and then expanded to a larger data set consisting of 22 cell images. The proposed algorithm is compared with original Otsu's method and existing improved algorithms. Four evaluation metrics including misclassification error, foreground recall, Dice similarity coefficient and Jaccard index are adopted to quantitatively measure the segmentation performance. Results show that the proposed algorithm achieves best segmentation results on both data sets quantitatively and qualitatively. The proposed algorithm adapts the Otsu's method to more image subtypes, indicating a wider application in automatic thresholding and image segmentation field.

The world is witnessing rapid transformations in hardware technology. This will keep on improving day by day. The processing power of every handheld device is significantly improved as well as the storage capacity is increased. With all these advancements, the personal video capture and usage of videos have tremendously increased across many applications. The quality assessment of personal videos has become very important. It is a vital task to design a model for assessing the video quality. A novel methodology for detecting damaged video frames is proposed here. The primary objective of the research is to detect uni-coloured frames and frames with ice effect. The novel histograms bin comparison technique is proposed for inter- and intraframe analysis. The shakiness of the video is calculated using motion estimation. The video quality is also assessed using blur detection as well as contrast calculation to spot useful portion in the video. The proposed framework generates the video quality metadata and supports the contextualisation process.

Image denoising using a combination of non-local self-similarity and transformed domain techniques has become popular in past few years. Instead of working on independent pixels, patches extracted from the noisy image are grouped together based on structural similarity and noise elimination is performed in transformed domain. Orthogonal locality preserving projection and its variant that processes the images directly in matrix format have been used for image denoising recently. Locality preserving nature of these techniques takes care of similarity within image patches while learning the basis, hence reducing the task of grouping patches explicitly. Non-local self-similarity based image denoising approaches perform patch grouping based on structural similarity. Discriminant information, if considered can play pivotal role in achieving superior clustering of data and thereby is expected to enhance the quality of denoising. With this aim in mind, two-dimensional (2D) orthogonal locality preserving discriminant projection is formulated in this study. While learning the basis, along with the similarity, proposed approach also takes into account dissimilarity between patches. A global basis thus learnt from the noisy image is used for denoising and comparable denoising performance is shown relative to the state-of-the-art methods.

In this study, a fuzzy classification approach based on colour features has been investigated to estimate the ripeness of apple fruits according to three maturity stages; unripe, turning-ripe and ripe. The K nearest neighbour algorithm was applied in order to segment the fruit image into four regions namely background, green area, yellow area and red area. The last three regions represent the colour features and were subsequently given as inputs to the fuzzy classifier. Gradient method has been used for tuning the fuzzy classifier in order to obtain the best performance. Image database used for simulation has been collected and exploited for the training and testing phases using cross-validation. Simulation results indicate that the best classifier parameters can be obtained. The efficiency of the proposed system compared with the non-use of the gradient method has been proved by the confusion matrix and the most known classification evaluation metrics. Moreover, the trained fuzzy classifier demonstrates its outperformance in terms of accuracy and execution time compared with other existing methods.

The authors propose an adaptive face recognition algorithm based on the discrete cosine transform (DCT) coefficients approach. For the database's establishment, the face images are pre-processed with colour transform, hair cutting, and background removing to eliminate non-face information. The recognised kernel applied the weights of DCT coefficient distribution with the entire image transformation, to avoid position mismatch and reduce the light effect. The key coefficients of DCT are chosen from the training database by maximum variance. The fast search mode can reject 90% weak candidates with few coefficients to fasten the processing speed. The significant coefficients weighting methods are used to enhance face features. Only using 50 coefficients per picture, the recognition rate can achieve 95% for ORL face database testing. For real-time recognition, camera imaging is processed with algorithms using C-programming based on Windows system. The recognition rate can achieve 95% and the speed is about nine frames per second for real-time recognition in practice.

To improve the boundary processing ability and anti-noise performance of image segmentation algorithm，a neutrosophic fuzzy clustering algorithm based on non-local information is proposed here. Initially, the proposed approach uses the data distribution of deterministic subset to determine the clustering centre of the fuzzy subset. Besides, the fuzzy non-local pixel correlation is introduced into the neutrosophic fuzzy mean clustering algorithm. The experimental results on synthetic images, medical images and natural images show that the proposed method is more robust and more accurate than the existing clustering segmentation methods.