TY - JOUR ID - 133006 TI - A Three-stage Filtering Approach for Face Recognition JO - International Journal of Engineering JA - IJE LA - en SN - 1025-2495 AU - Hassanpour, H. AU - Ghasemi, M. AD - Computer Engineering and IT Department, Shahrood University of Technology, Shahrood, Iran Y1 - 2021 PY - 2021 VL - 34 IS - 8 SP - 1856 EP - 1864 KW - Face recognition KW - Image Hashing KW - Local Sensitive Hashing KW - Large Datasets DO - 10.5829/ije.2021.34.08b.06 N2 - Face recognition has become a crucial topic in recent decades, which offers important opportunities for applications in security surveillance, human-computer interaction, and forensics. However, it poses challenges, including uncontrolled environments, large datasets, and insufficiency of training data. In this paper, a face recognition system is proposed to iron out the above problems with a new framework based on a hashing function in a three-stage filtering approach. At the first stage, candidate subjects are chosen using the Locality-Sensitive Hashing (LSH) function. We employ a voting system to select candidates via disregarding a large number of dissimilar identities considering their local features. At the second stage, a robust image hashing based on Discrete Cosine Transform (DCT) coefficients is used to further refine the candidate images in terms of global visual information. Finally, the test image is recognized among selected identities using other visual information, resulting in further accuracy gains. Extensive experiments on FERET, AR, and ORL datasets show that the proposed method outperforms with a significant improvement in accuracy over the state-of-the-art methods. UR - https://www.ije.ir/article_133006.html L1 - https://www.ije.ir/article_133006_27dbb1088f264b9afb187a55032e4938.pdf ER -