Abstract ▼ AI-Helper

In this study, through the design of proposed Polynomial-based Radial Basis Function Neural Networks, recognition module part in composition essential part in overall face recognition system show a solution about face image data has a high-dimensional pattern recognition problem. First, in preproces...

In this study, through the design of proposed Polynomial-based Radial Basis Function Neural Networks, recognition module part in composition essential part in overall face recognition system show a solution about face image data has a high-dimensional pattern recognition problem. First, in preprocessing step, we use a CCD camera to receive a frame in real-time. Using histogram equalization method enhance a image that prevented in effect of illumination. We use a AdaBoost algorithm or other preprocessing algorithms (ex. FLC, Intensity Adjust, Image multiplication, Adaptive Histogram) that Viola and Jones are proposed to face detection between face image and non-face image. And face image formed high-dimension information to reduce a dimension we use a PCA method and LDA method that used in general. Secondly, we design a pRBFNNs to identify ID with each person has a unique pattern. The proposed pRBFNN architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNN is represented as three kinds of polynomials such as constant, linear, and quadratic. Coefficients of connection weight identified with back-propagation using gradient descent method. The output of pRBFNN model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of the Particle Swarm Optimization. The proposed pRBFNNs is applied to face image(ex ORL, Yale, JAFFE) dataset. And we design the face recognition system.

주제어