1Lowe D G. Distinctive image features from scale-invariant keypoints[J].{H}International Journal of Computer Vision,2004,(2):91-110.
2Dalal N,Triggs B. Histograms of oriented gradients for human detection[A].San Diego,CA,USA:IEEE,2005.886-893.
3Ojala T,Pietikainen M,Harwood D. Performance evaluation of texture measures with classification based on Kullback discrimination of distributions[A].Jerusalem,Irsael:IEEE,1994.582-585.
4Matas J,Chum O,Urban M. Robust wide-baseline stereo from maximally stable extremal regions[J].{H}IMAGE AND VISION COMPUTING,2004,(10):761-767.
5Hinton G E,Osindero S,Teh Y W. A fast learning algorithm for deep belief nets[J].{H}Neural Computation,2006,(7):1527-1554.
6Hinton G E. Learning multiple layers of representation[J].{H}Trends in Cognitive Sciences,2007,(10):428-434.
7Hinton G E,Zemel R S. Autoencoders,minimum description length,and Helmholtz free energy[A].Burlington,USA:Morgan Kaufmann,1994.3-10.
8Rumelhart D E,Hinton G E,Williams R J. Learning Representations by Back-Propagating Errors[M].Cogmitive Modeling:MIT Press,2002.213.
9Vincent P,Larochelle H,Bengio Y. Extracting and composing robust features with denoising autoencoders[A].New York,NY,USA:ACM,2008.1096-1103.
10Lee H,Grosse R,Ranganath R. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations[A].New York,NY,USA:ACM,2009.609-616.