Autori: I. Buciu, C. Kotropoulos and I. Pitas

Editorial: Proc. 2003 IEEE International Conference on Image Processing (ICIP 2003), Barcelona, Spain, p.1054 – 105, 2003.

Rezumat:

Two hybrid systems for classifying seven categories of human facial expression are proposed. The first system combines independent component analysis (ICA) and support vector machines (SVMs). The original face image database is decomposed into linear combinations of several basis images, where the corresponding coefficients of these combinations are fed up into SVMs instead of an original feature vector comprised of grayscale image pixel values. The classification accuracy of this system is compared against that of baseline techniques that combine ICA with either two-class cosine similarity classifiers or two-class maximum correlation classi£ers, when we classify facial expressions into these seven classes. We found that, ICA decomposition combined with SVMs outperforms the aforementioned baseline classifiers. The second system proposed operates in two steps: first, a set of Gabor wavelets (GWs) is applied to the original face image database and, second, the new features obtained are classified by using either SVMs or cosine similarity classi£ers or maximum correlation classifier. The best facial expression recognition rate is achieved when Gabor wavelets are combined with SVMs.

Cuvinte cheie: Independent Component Analysis, Gabor wavelets, facial expression recognition

URL: http://poseidon.csd.auth.gr/EN/