The edge-aware bilateral filter has been demonstrated to be effective for preserving depth edges, and disparity maps obtained from Fast Bilateral Stereo (FBS) have enhanced the efficiency of algorithm and the robustness to noise. However, they also lead to a non-perfect localisation of discontinuities. To overcome this issue, a new bilateral filtering based cost aggregation utilising colour statistical classification and similarity measurement within annular blocks is proposed in this study. We have adopted the similarity of histograms evaluated by Earth Mover Distance (EMD) to obtain the raw matching cost in the raised annular block, since histograms are very effective and efficient in capturing the distribution characteristics of visual features. For the weights aggregation, the spatial weight is assumed to be a constant. The colour weight is calculated by using a cluster-mean-value strategy, which is implemented by the local colour histogram. It improves the accuracy in the discontinuous areas. Computation redundancy is reduced by disparity candidate selection using the local minimal relevancy in the corresponding annular blocks. We use the efficiency and accuracy to demonstrate the performance of our proposed method. Experimental results have shown that the proposed method reduces the mismatch at depth discontinuous and the computation complexity significantly.

This study proposes a new feature descriptor, local directional mask maximum edge pattern, for image retrieval and face recognition applications. Local binary pattern (LBP) and LBP variants collect the relationship between the centre pixel and its surrounding neighbours in an image. Thus, LBP based features are very sensitive to the noise variations in an image. Whereas the proposed method collects the maximum edge patterns (MEP) and maximum edge position patterns (MEPP) from the magnitude directional edges of face/image. These directional edges are computed with the aid of directional masks. Once the directional edges (DE) are computed, the MEP and MEPP are coded based on the magnitude of DE and position of maximum DE. Further, the robustness of the proposed method is increased by integrating it with the multiresolution Gaussian filters. The performance of the proposed method is tested by conducting four experiments onopen access series of imaging studies-magnetic resonance imaging, Brodatz, MIT VisTex and Extended Yale B databases for biomedical image retrieval, texture retrieval and face recognition applications. The results after being investigated the proposed method shows a significant improvement as compared with LBP and LBP variant features in terms of their evaluation measures on respective databases.

In this study, first a supervised version for probabilistic principal component analysis mixture model is proposed. Using this model, local linear underlying manifolds of data samples are obtained. These underlying manifolds are used in a dimensionality reduction without loss framework, for face recognition application. In this framework, the benefits of dimensionality reduction are used in the predictive model, while using the projection penalty idea, the loss of useful information will be minimised. The authors use support vector machine (SVM) and k-nearest neighbour (KNN) classifiers as the predictive models in this framework. To train and evaluate the proposed method, the well-known face databases are used. The experimental results show that the proposed method with SVM as the predictive model have the most average classification accuracy compared with many traditional methods which use predictive model SVM after dimensionality reduction, and also compared with the projection penalty idea used for linear and non-linear kernel-based dimensionality reduction methods. Moreover, their experiments show that the proposed method with KNN as predictive model is superior to the case that dimensionality reduction is performed, and then the KNN classifier is applied.

A recently developed sparse representation algorithm, has been proved to be useful for multi-object tracking and this study is a proposal for developing its parallelisation. An online dictionary learning is used for object recognition. After detection, each moving object is represented by a descriptor containing its appearance features and its position feature. Any detected object is classified and indexed according to the sparse solution obtained by an orthogonal matching pursuit (OMP) algorithm. For a real-time tracking, the visual information needs to be processed very fast without reducing the results accuracy. However, both the large size of the descriptor and the growth of the dictionary after each detection, slow down the system process. In this work, a novel accelerating OMP algorithm implementation on a graphics processing unit is proposed. Experimental results demonstrate the efficiency of the parallel implementation of the used algorithm by significantly reducing the computation time.

Image keypoint descriptor matching is an important pre-processing task in various computer vision applications. This study first introduces an existing multi-resolution exhaustive search (MRES) algorithm combined with a multi-resolution candidate elimination technique to address this issue efficiently. A graphics processing unit (GPU) acceleration design is then proposed to improve its real-time performance. Suppose that a scale-invariant feature transform like algorithm is used to extract image keypoint descriptors of an input image, the MRES algorithm first computes a multi-resolution table of each keypoint descriptor by using a L ₁-norm-based dimension reduction approach. Next, a fast candidate elimination algorithm is employed based on the multi-resolution tables to remove all non-candidates from a candidate matching list by using a simple L ₁-norm computation. However, when the MRES algorithm was implemented on the central processing unit, the authors observed that the step of multi-resolution table building is not computationally efficient, but it is very suitable for parallel implementation on the GPU. Therefore, this study presents a GPU acceleration method for the MRES algorithm to achieve better real-time performance. Experimental results validate the computational efficiency and matching accuracy of the proposed algorithm by comparing with three existing methods.

This study presents supervised framework for automatic recognition and retrieval of interactions (SAFARRIs), a supervised learning framework to recognise interactions such as pushing, punching, and hugging, between a pair of human performers in a video shot. The primary contribution of the study is to extend the vectors of locally aggregated descriptors (VLADs) as a compact and discriminative video encoding representation, to solve the complex class partitioning problem of recognising human interaction. An initial codebook is generated from the training set of video shots, by extracting feature descriptors around the spatiotemporal interest points computed across frames. A bag of action words is generated by encoding the first-order statistics of the visual words using VLAD. Support vector machine classifiers (1 against all) are trained using these codebooks. The authors have verified SAFARRI's accuracy for classification and retrieval (query by example). SAFARRI is free from tracking or recognition of body parts and capable of identifying the region of interaction in video shots. It gives superior retrieval and classification performances over recently proposed methods, on two publicly available human interaction datasets.

Gender classification is one of the most challenging problems in computer vision. Facial gender detection of neonates and children is also known as a highly demanding issue for human observers. This study proposes a novel gender classification method using frontal facial images of people. The proposed approach employs principal component analysis (PCA) and fuzzy clustering technique, respectively, for feature extraction and classification steps. In other words, PCA is applied to extract the most appropriate features from images as well as reducing the dimensionality of data. The extracted features are then used to assign the new images to appropriate classes – male or female – based on fuzzy clustering. The computational time and accuracy of the proposed method are examined together and the prominence of the proposed approach compared to most of the other well-known competing methods is proved, especially for younger faces. Experimental results indicate the considerable classification accuracies which have been acquired for FG-Net, Stanford and FERET databases. Meanwhile, since the proposed algorithm is relatively straightforward, its computational time is reasonable and often less than the other state-of-the-art gender classification methods.