| Hi-index | 0.00 |
A novel method for face recognition using profile images based on the representation of the original and morphological derived profile shapes is presented in this paper. The goal of our approach is to use information from profile outline that bounds the face and the hair. A grey-level profile image is thresholded to produce a binary image, representing the face region. After normalizing the area and orientation of this shape using basic morphological operations, dilation and erosion, we simulate hair growth and haircut and produce two new profile silhouettes. From this three profile shapes feature vectors are obtained using distances between outline curve points and shape centroid. After normalizing the vector components, the Euclidean distance measure is used for measuring the similarity of the feature vectors derived from different profiles. Experiments were performed on profile images of thirty persons. Experimental results including recognition rates are presented and discussed.