| Description |
ix, 119 leaves : illustrations ; 28 cm. |
| Summary |
"In the present work, an automatic Facial Expression Recognition (FER) system is developed based on Gabor-wavelet methodology and learning vector quantization networks (LVQ). Facial attributes from the frontal images are extracted in the form of feature vectors by evaluating the responses from a set of 18 complex Gabor filters at 34 reference points on a face. The resultant high-dimensional feature vectors are condensed by performing Principal Component Analysis (PCA) coupled with Singular Value Decomposition (SVD) and are classified into classes of expression: anger, distress, sad, surprise, normal and happy, using LVQ networks"--Abstract, leaf iii. |
|
