In this research work, we propose a method for human action recognition based on the combination of structural and temporal features. The pose sequence in the video is considered to identify the action type. The structural variation features are obtained by detecting the angle made between the joints during the action, where the angle binning is performed using multiple thresholds. The displacement vector of joint locations is used to compute the temporal features. The structural variation features and the temporal variation features are fused using a neural network to perform action classification. We conducted the experiments on different categories of datasets, namely, KTH, UTKinect, and MSR Action3D datasets. The experimental results exhibit the superiority of the proposed method over some of the existing state-of-the-art techniques.

Advancement in technology has made the acquisition and storage of multimedia data easy and inexpensive to the end user. However for effective use of the information available in the multimedia, efficient and accurate retrieval methods are required. Multimedia based retrieval systems extensively used texture based approach to interpret and recognize a scene image. The texture of an image provides clue to the orientation, smoothness, symmetry, shape, regularity and coarness of the surface. The Local Binary Pattern Variance (LBPV) is a texture feature where variance in contrast acts as adaptive factor during computation of local binary pattern (LBP) histogram. The LBP combines both structural and statistical approaches to texture analysis. This paper proposes an LBP Variance based approach to visual content based video retrieval. The proposed approach uses query by example paradigm for retrieving similar clips from the video. Experiments conducted on TRECVID dataset shows the efficacy of proposed approach

In this paper, video shot boundary detection method based on Gabor moments is proposed. Each video frame is convolved with six 2-D Gabor filters corresponding to six different orientations, and the first and second moments of these convolved images are obtained, generating twelve dimensional feature vector. The frame dissimilarity values are compared against an adaptive threshold to localize the shot. Experimentation on the TRECVID video segments have been done to demonstrate the performance of the proposed approach for both cut and fade detection. The comparative study with other approaches is included to exhibit the superiority of the proposed approach in terms of efficiency and accuracy of shot detection.

In this work, we present a new 3D face recognition method based on Speeded-Up Local Descriptor (SULD) of significant points extracted from the range images of faces. The proposed model consists of a method for extracting distinctive invariant features from range images of faces that can be used to perform reliable matching between different poses of range images of faces. For a given 3D face scan, range images are computed and the potential interest points are identified by searching at all scales. Based on the stability of the interest point, significant points are extracted. For each significant point we compute the SULD descriptor which consists of vector made of values from the convolved Haar wavelet responses located on concentric circles centred on the significant point, and where the amount of Gaussian smoothing is proportional to the radii of the circles. Experimental results show that the newly proposed method provides higher recognition rate compared to other existing contemporary models developed for 3D face recognition.