Translator Disclaimer
15 February 2007 Learning optimal features for visual pattern recognition
Author Affiliations +
Proceedings Volume 6492, Human Vision and Electronic Imaging XII; 64920B (2007)
Event: Electronic Imaging 2007, 2007, San Jose, CA, United States
The optimal coding hypothesis proposes that the human visual system has adapted to the statistical properties of the environment by the use of relatively simple optimality criteria. We here (i) discuss how the properties of different models of image coding, i.e. sparseness, decorrelation, and statistical independence are related to each other (ii) propose to evaluate the different models by verifiable performance measures (iii) analyse the classification performance on images of handwritten digits (MNIST data base). We first employ the SPARSENET algorithm (Olshausen, 1998) to derive a local filter basis (on 13 × 13 pixels windows). We then filter the images in the database (28 × 28 pixels images of digits) and reduce the dimensionality of the resulting feature space by selecting the locally maximal filter responses. We then train a support vector machine on a training set to classify the digits and report results obtained on a separate test set. Currently, the best state-of-the-art result on the MNIST data base has an error rate of 0,4%. This result, however, has been obtained by using explicit knowledge that is specific to the data (elastic distortion model for digits). We here obtain an error rate of 0,55% which is second best but does not use explicit data specific knowledge. In particular it outperforms by far all methods that do not use data-specific knowledge.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kai Labusch, Udo Siewert, Thomas Martinetz, and Erhardt Barth "Learning optimal features for visual pattern recognition", Proc. SPIE 6492, Human Vision and Electronic Imaging XII, 64920B (15 February 2007);


Object detection based on deformable part model
Proceedings of SPIE (September 27 2016)
Morphological component analysis
Proceedings of SPIE (September 17 2005)
Template basis techniques for pattern recognition
Proceedings of SPIE (October 23 1996)
On the selection of ICA features for texture classification
Proceedings of SPIE (October 30 2009)

Back to Top