Research
Implementation of Back Propagation Neural Network with PCA for Face Recognition
Face recognition is truly one of the demanding fields of biometric image processing system. Within this paper, we have implemented Back Propagation Neural Network for face recognition using MATLAB, where feature extraction and face identification system completely depend on Principal Component Analysis (PCA). Face images are multidimensional and variable data. Hence we cannot directly apply Back Propagation Neural Network to classify face without extracting the core area of face. So, the dimensionality of face image is reduced by the Principal Component Analysis algorithm then we have to explore unique feature for all stored database images called eigenfaces of eigenvectors. These unique features or eigenvectors are given as parallel input to the Back Propagation Neural Network (BPNN) for recognition of given test images. Here test image is taken from the integrated webcam which is applied to the BPNN trained network. The maximum output of the tested network gives the index of recognized face image. BPNN employing PCA is more robust and reliable than PCA based face recognition system.
Implementation and Performance Analysis of Different Hand Gesture Recognition Methods
In recent few years, hand gesture recognition is one of the advanced grooming technologies in the era of human-computer interaction and computer vision due to a wide area of application in the real world. But it is a very complicated task to recognize hand gesture easily due to gesture orientation, light condition, complex background, translation and scaling of gesture images. To remove this limitation, several research works have developed which is successfully decrease this complexity. However, the intention of this paper is proposed and compared four different hand gesture recognition system and apply some optimization technique on it which ridiculously increased the existing model accuracy and model running time. After employed the optimization tricks, the adjusted gesture recognition model accuracy was 93.21% and the run time was 224 seconds which was 2.14% and 248 seconds faster than an existing similar hand gesture recognition model. The overall achievement of this paper could be applied for smart home control, camera control, robot control, medical system, natural talk, and many other fields in computer vision and human-computer interaction.
