G.M. Mamun-Al-Imran's research while affiliated with Khulna University and other places

This paper presents an iris recognition framework to recognize irises from distantly acquired face images using image gradient-based feature extraction and K-Nearest Neighbor with various distance classifiers. The work herein applies the gradient local auto-correlation descriptor to extract discriminative features from the iris images and to reduce feature dimensionality by optimizing some parameters. Several distance metrics are applied in the iris classification stage to reduce computational complexity and build the classification models. The proposed framework effectively handles the noisy artefacts, rotation, occlusion, and illumination variation challenges. The experiments are carried out on a publicly accessible CASIA-V4 distance database to ascertain the effectiveness of distant iris recognition and to compare the efficacy of several existing distant classifiers. The experimental results justify that distance metrics influence the recognition outcomes of the classifier significantly, and the recognition performance of the Correlation distance metric is better than the other distance classifiers for iris gradient features.

Nowadays, human action recognition (HAR) has become an emerging research topic for movie understanding, video clip retrieval, human-computer interactions, autonomous driving systems etc. This paper introduces an efficacious feature representation strategy and novel framework for identifying human action by employing depth motion maps (DMMs) based on adaptive thresholding technique. Firstly, each 3D depth frame is projected onto three orthogonal Cartesian planes to form 2D projected maps and concatenating the front view, side view and top view to generate the DMM features.The DMMs capture the motion characteristics from the video sequence. After that, we have adopted adaptive thresholding for separating image objects from video sequence based on pixel intensities so that the radial basis kernel based support vector machine (SVM) are used to classify and recognize the action sequences effitively. We carried out the experiment on MSR-Action3D action dataset and evaluated the classification performance by measuring confusion matrices to provide details and visualization about recognized actions. From the experimental results, we reveal that the proposed framework attains always better performance than other competitive methods on this database.