In this paper, we have proposed a system for reliable communication of coded grayscale facial imagesover noisy channels. Principle Component Analysis (PCA) is used for face dimensional reduction and facerecognition and Repeated Bit Representation (RBR) is proposed to code the eigenfaces for mobile communicationapplications. Recognition obtained with RBR system approach reaches to %82 for 80 test images (2 poses perperson) and 320 training images (8 poses per person) of ORL, by considering only the most important 30coefficients of principle components in a noisy channel with SNR=-2dB.
展开▼