7 search results - page 1 / 2 » Recognition of handwritten digits using sparse codes generat... |
ESANN
2006
13 years 6 months ago
2006
We investigate when sparse coding of sensory inputs can improve performance in a classification task. For this purpose, we use a standard data set, the MNIST database of handwritte...
ICDAR
2007
IEEE
13 years 11 months ago
2007
IEEE
We describe an unsupervised learning algorithm for extracting sparse and locally shift-invariant features. We also devise a principled procedure for learning hierarchies of invari...
ICASSP
2009
IEEE
13 years 11 months ago
2009
IEEE
Local features are widely used for content-based image retrieval and object recognition. We present an efficient method for encoding digital images suitable for local feature extr...
CVPR
2009
IEEE
14 years 11 months ago
2009
IEEE
In this paper we present a method for learning classspecific
features for recognition. Recently a greedy layerwise
procedure was proposed to initialize weights of deep
belief ne...
ICCV
2005
IEEE
14 years 6 months ago
2005
IEEE
Visual codebook based quantization of robust appearance descriptors extracted from local image patches is an effective means of capturing image statistics for texture analysis and...