Comparing Transform Domain Techniques and Vector Quantization Techniques for Face Detection and Recognition in Digital Images

Many face recognition algorithms have been proposed that help faces to be identified on systems. The aim of the paper is to compare the performance of transform domain techniques and Vector Quantization techniques. The system considers the full and partial feature vector sizes of images. In addition to this, the proposed system tries to improvise by extracting the face region before feature extraction is done. The system recognizes the face region using YCbCr color space to reduce the effect of lightening positions and intensities.

Provided by: University of Muenster Topic: Security Date Added: Jul 2012 Format: PDF

Find By Topic