Evaluation of image preprocessing techniques for eigenface-based face recognition

摘要: We present a range of image processing techniques as potential pre-processing steps, which attempt to improve the performance eigenface method face recognition. Verification tests are carried out by applying thresholds gather false acceptance rate (FAR) and rejection (FRR) results from data set comprised images that typical difficulties when attempting recognition, such strong variations in lighting direction intensity, partially covered faces changes facial expression. Results compared using equal error (EER), is FAR FRR. determine most successful methods be used with based application areas security, surveillance, compression archive searching.