The role of local scale and orientation in feature location using neural nets
作者： P.J.G. Lisboa , M. Mallaiah
关键词:
摘要: The application of one pass orientation and scale selective filters to feature location is investigated. particular case study developed deals with the eyes in head-and-shoulders images using artificial neural networks trained by back-error-propagation. Three types were studied. Conventional Marr edge detectors, Gabor horizontal vertical directions, also detectors which extract high resolution information along each two directions 2D separable wavelet filters. Tests conducted locate centre pupil right eye sixty images. results are compared for different filters, raw pixel image directly. >
sci-hub.se 参考文章(5)
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams, Learning representations by back-propagating errors Nature. ,vol. 323, pp. 696- 699 ,(1988) , 10.1038/323533A0
Theory of Edge Detection Proceedings of The Royal Society B: Biological Sciences. ,vol. 207, pp. 187- 217 ,(1980) , 10.1098/RSPB.1980.0020
J.G. Daugman, Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 36, pp. 1169- 1179 ,(1988) , 10.1109/29.1644
S.G. Mallat, A theory for multiresolution signal decomposition: the wavelet representation IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 11, pp. 674- 693 ,(1989) , 10.1109/34.192463
P. J. G. Lisboa, Image Classification Using Gabor Representations with a Neural Net Springer, Dordrecht. pp. 112- 127 ,(1992) , 10.1007/978-94-011-2360-0_8