Class specific subspace dependent nonlinear correlation filtering for illumination tolerant face recognition
| Autor: | Pradipta K. Banerjee, Asit K. Datta |
|---|---|
| Rok vydání: | 2014 |
| Předmět: |
Digital image correlation
Pixel business.industry Pattern recognition Filter (signal processing) Facial recognition system Artificial Intelligence Phase correlation Frequency domain Face (geometry) Signal Processing Computer Vision and Pattern Recognition Artificial intelligence business Software Subspace topology Mathematics |
| Zdroj: | Pattern Recognition Letters. 36:177-185 |
| ISSN: | 0167-8655 |
| DOI: | 10.1016/j.patrec.2013.10.012 |
| Popis: | A frequency domain nonlinear correlation technique for face recognition under varying lighting conditions is proposed. The technique is based on phase correlation between an optimum projecting image correlation filter and an optimum reconstructed image correlation filter during class specific subspace operation. Performance improvement is achieved by exploiting point wise nonlinearities of image pixels. Further optimization is carried out by minimizing the energy at the correlation plane while maximizing the correlation peak. While comparing with other standard unconstrained correlation filters, improved performance of the proposed scheme is established by experimental results on standard face data bases. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect