Stockwell transform based face recognition: A robust and an accurate approach
| Autor: | B. H. Shekar, D. S. Rajesh |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
business.industry
Computer science Gaussian ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Short-time Fourier transform 020206 networking & telecommunications 02 engineering and technology Gabor transform Facial recognition system symbols.namesake Face (geometry) 0202 electrical engineering electronic engineering information engineering symbols 020201 artificial intelligence & image processing Computer vision Artificial intelligence Focus (optics) business S transform |
| Zdroj: | ICACCI |
| DOI: | 10.1109/icacci.2016.7732042 |
| Popis: | In this work, we have designed a local and a global descriptor based on the Stockwell transform. The Stockwell transform time frequency distribution plot possesses a better time frequency resolution than the Gabor transform (the short term Fourier transform (STFT) with a Gaussian window) time frequency distribution. The imaginary part of the Stockwell transform time frequency distribution is found to be robust against illumination variation. Hence it must be possible to design better descriptors using the Stockwell transform. We have investigated this concept keeping face recognition problem in focus. Our experiments conducted on well known face databases with pose, light and expression variations have demonstrated the discriminative capability of our descriptors. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|