Face recognition using wavelets and fuzzy C-means clustering

In this paper we perform wavelet transform of the input 256×256 color image and decompose input image into low-pass and high-pass components. After finding the position of face using the histogram of the edges, a face region in low-pass band image is extracted. Since RGB color image is easily affected by illumination, the image of low pass component is normalized, and a face region is detected using face color information. In this paper, we use 3000 images of 10 persons, and KL transform is applied in order to classify face vectors effectively. FCM (Fuzzy C-means) algorithm classifies face vectors, which have similar features, into the same cluster. In this case, the number of cluster is equal to that of a person, and the mean vector of each cluster is used as codebook. We estimate the proposed system´s performance through experiments. The recognition rate of learning images and that of testing image are computed using correlation coefficients and Euclidean distance