Learning a discriminative sparse tri-value transform

Zhenhua Qui*, Guoping Qiu, Pong Chi Yuen

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review


Simple binary patterns have been successfully used for extracting feature representations for visual object classification. In this paper, we present a method to learn a set of discriminative tri-value patterns for projecting high dimensional raw visual inputs into a low dimensional subspace for tasks such as face detection. Unlike previous methods that use predefined simple transform bases to generate tens of thousands features first and then use nlachine learning to select the most useful features, our method attempts to learn discriminative transform bases directly. Since it would be extremely hard to develop analytical solutions, we define an objective function that can be solved using simulated annealing. To reduce the search space, we impose sparseness and smoothness constraints on the transform bases. Experimental results demonstrate that our method is effective and provides an alternative approach to effective visual object class-fication.

Original languageEnglish
Title of host publication2008 19th International Conference on Pattern Recognition, ICPR 2008
Publication statusPublished - 2008
Event2008 19th International Conference on Pattern Recognition, ICPR 2008 - Tampa, FL, United States
Duration: 8 Dec 200811 Dec 2008

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651


Conference2008 19th International Conference on Pattern Recognition, ICPR 2008
Country/TerritoryUnited States
CityTampa, FL

Scopus Subject Areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Learning a discriminative sparse tri-value transform'. Together they form a unique fingerprint.

Cite this