Face recognition using 3D scans can be achieved by many approaches, but most of these approaches are based on high quality depth sensors. In this paper, the authors use the normal maps obtained from... Show More

Face recognition using 3D scans can be achieved by many approaches, but most of these approaches are based on high quality depth sensors. In this paper, the authors use the normal maps obtained from the Kinect sensor to investigate the usefulness of data augmentation and signal-level fusion derived from depth data captured by a low quality sensor. In this face recognition process, the authors first preprocess the captured 3D scan of each person by cropping the face and reducing the noise; normals are computed and separated into three maps: Nx, Ny, and Nz. the authors combine the three normal maps to form an RGB image; these images are used to train a convolutional neural network. The authors investigate the order of components that yields to the best accuracy and compare it with previous results obtained on CurtinFaces and KinectFaceDB databases, achieving rank one identification rate of 94.04% and 91.35%, respectively.

The future of computer vision lies in deep learning to develop machines to solve our human problems. One of the most important areas of research is smart video surveillance. This feature is related... Show More

The future of computer vision lies in deep learning to develop machines to solve our human problems. One of the most important areas of research is smart video surveillance. This feature is related to the study and recognition of movements, and it's used in many fields, like security, sports, medicine, and a whole lot of new applications. The study and analysis of human activity is very important to improve because it is a very sensitive field, like in security, the human needs a machine's help a lot; and in recent years, developers have adopted many advanced algorithms to discover the type of movements humans preform, and the results differ from one to another. The most important part of human activity recognition is real time, so one can detect any issue, like a medical problem, in time. In this regard, the authors will use methods of deep learning to reach a good result of recognition of the nature of human action in real time clips.

In spite of the great progress in research work related to the smart antenna field, obtaining an efficient beamforming technique with low complexity, fast converge, and better other performance... Show More

In spite of the great progress in research work related to the smart antenna field, obtaining an efficient beamforming technique with low complexity, fast converge, and better other performance remains the preferred objective of most researchers. The present work proposes a new version of least mean square (LMS) approach for the beamforming of smart antenna array. The novelty of the proposed algorithm versus its basic version is focalized in its dependence on a new initialization technique, whose aim is to accelerate convergence speed and maintain, at the same time, the algorithm simplicity. The central idea of the proposed technique, which is named new initialized LMS (NI-LMS), is to compute an initial weight vector using only a diagonal matrix extracted from the spatial auto-covariance matrix. Simulation examples are carried out on linear antenna array to demonstrate and validate the effectiveness of the new method. In addition, the computational complexity of the new proposition is analyzed and compared to that of the conventional LMS beamforming approach.