Face Detection from still and Video Images using Unsupervised Cellular Automata with K means clustering algorithm
This addresses the problem of face detection and recognition in computer vision, but it appears incremental as it combines existing techniques like skin color detection, cellular automata, and neural networks.
The paper tackles face detection and recognition from still and video images by identifying skin pixels, locating facial features, and using an RBF neural network, achieving reliable performance for faces with varying orientations and expressions.
Pattern recognition problem rely upon the features inherent in the pattern of images. Face detection and recognition is one of the challenging research areas in the field of computer vision. In this paper, we present a method to identify skin pixels from still and video images using skin color. Face regions are identified from this skin pixel region. Facial features such as eyes, nose and mouth are then located. Faces are recognized from color images using an RBF based neural network. Unsupervised Cellular Automata with K means clustering algorithm is used to locate different facial elements. Orientation is corrected by using eyes. Parameters like inter eye distance, nose length, mouth position, Discrete Cosine Transform (DCT) coefficients etc. are computed and used for a Radial Basis Function (RBF) based neural network. This approach reliably works for face sequence with orientation in head, expressions etc.