Method and apparatus for object recognition using probability models

作者: Sergey Ioffe

DOI:

关键词: Representation (systemics)Object (computer science)Computer scienceDigital imageCognitive neuroscience of visual object recognitionComputer visionMethodPattern recognitionImage (mathematics)Gaussian network modelFeature (computer vision)Artificial intelligence

摘要: A method and an apparatus automatically recognize or verify objects in a digital image using probability models. According to first aspect, by: accessing data including object of interest therein; detecting the image; normalizing generate normalized representation; extracting plurality features from applying each feature previously-determined additive model determine likelihood that belongs existing class. In one embodiment, is Additive Gaussian Model.

参考文章(24)
Thomas Leung, Jitendra Malik, Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons International Journal of Computer Vision. ,vol. 43, pp. 29- 44 ,(2001) , 10.1023/A:1011126920638
Michael Collins, Robert E. Schapire, Yoram Singer, Logistic Regression, AdaBoost and Bregman Distances conference on learning theory. ,vol. 48, pp. 158- 169 ,(2000) , 10.1023/A:1013912006537
Mingjing Li, Hong-Jiang Zhang, Longbin Chen, Lei Zhang, Face annotation for photo management ,(2003)
Mohan M. Trivedi, Kohsia S. Huang, Digital processing of video images ,(2003)
P.Jonathon Phillips, Harry Wechsler, Jeffery Huang, Patrick J. Rauss, The FERET database and evaluation procedure for face-recognition algorithms Image and Vision Computing. ,vol. 16, pp. 295- 306 ,(1998) , 10.1016/S0262-8856(97)00070-X
Roderick Murray-Smith, Daniel Sbarbaro, Nonlinear adaptive control using nonparametric Gaussian process prior models IFAC Proceedings Volumes. ,vol. 35, pp. 325- 330 ,(2002) , 10.3182/20020721-6-ES-1901.01040
Pentland, Moghaddam, Starner, View-based and modular eigenspaces for face recognition computer vision and pattern recognition. pp. 84- 91 ,(1994) , 10.1109/CVPR.1994.323814