Parallel AdaBoost algorithm for gabor wavelet selection in face recognition
Proceedings of the International Conference on Image Processing, ICIP 2008, October 12–15, 2008, San Diego, California, USA, pp. 1640–1643
Abstract
In this paper, the problem of automatic Gabor wavelet selection for face recognition is tackled by introducing an automatic algorithm based on Parallel AdaBoosting method. Incorporating mutual information into the algorithm leads to the selection procedure not only based on classification accuracy but also on efficiency. Effective image features are selected by using properly chosen Gabor wavelets optimised with Parallel AdaBoost method and mutual information to get high recognition rates with low computational cost. Experiments are conducted using the well-known FERET face database. In proposed framework, memory and computation costs are reduced significantly and high classification accuracy is obtained.
Abstract sourceThis 2008 ICIP paper presents a method for selecting Gabor-wavelet features for face recognition using Parallel AdaBoost and mutual information. The reported evaluation uses a subset of the FERET face database.
Summary
The paper addresses the computational cost of selecting Gabor-wavelet features for face recognition. It combines Parallel AdaBoost, which parallelizes part of the boosting process by modeling sample-weight dynamics, with mutual information, a measure used here to identify redundant candidate features. The authors evaluate the approach on a subset of the FERET face database and report recognition results in the paper. This is a benchmark evaluation; the available sources do not establish prospective or clinical validation.
Cite this work
Ulas Bagci; Li Bai (2008). Parallel AdaBoost algorithm for gabor wavelet selection in face recognition. Proceedings of the International Conference on Image Processing, ICIP 2008, October 12–15, 2008, San Diego, California, USA, pp. 1640–1643 https://doi.org/10.1109/ICIP.2008.4712086
BibTeX