Search

Face recognition has received enormous fame in the field of pattern recognition and computer vision. Being a demanding area intensive research has been done by many researchers for more than a decade. However no standard technique exists for extracting the significant features of facial images in different categories. Techniques found in literature produces high accuracy but are computationally expensive which are not applicable in real time applications. In this paper, two well known methods, Discrete Wavelet Transform (DWT) and Weber Local Descriptor (WLD) are used to extract the face discriminative features. First for both types of features, the recognition accuracy is separately measured. In the next step, both types of features are fused using the concatenation method to improve the accuracy rate. To select more discriminative features and reduce data dimensions, computationally efficient algorithm (Kruskal-Wallis) is used. In the last step, three classifiers (SVM, KNN and BPNN) ensemble to improve the accuracy rate. Proposed technique is more efficient in terms of time complexity as compared to GA and PSO. Yale face database is used for all experiments. The proposed technique is highly robust to facial variations like occlusion, illumination and expression change and computationally efficient as compared to existing methods. [ABSTRACT FROM AUTHOR]

Gender recognition from facial images plays an important role in biometric applications. Employing Dyadic wavelet Transform (DyWT) and Local Binary Pattern (LBP), we propose a new feature descriptor DyWT-LBP for gender recognition. DyWT is a multi-scale image transformation technique that decomposes an image into a number of sub-bands which separate the features at different scales. DyWT is a kind of translation invariant wavelet transform that has a better potential for detection than Discrete Wavelet Transform (DWT). On the other hand, LBP is a texture descriptor and is known to be the best for representing texture micro-patterns, which play a key role in the discrimination of different objects in an image. For DyWT, we used spline dyadic wavelets (SDW). There exist many types of SDW; we investigated a number of SDWs for finding the best SDW for gender recognition. The dimension of the feature space generated by DyWT-LBP descriptor becomes excessively high. To tackle this problem, we apply a feature subset selection (FSS) technique that not only reduces the number of features significantly but also improves the recognition accuracy. Through a large number of experiments performed on FERET and Multi-PIE databases, we report for DyWT-LBP descriptor the parameter settings, which result in the best accuracy. The proposed system outperforms the stat of the art gender recognition approaches; it achieved a recognition rate of 99.25% and 99.09% on FERET and Multi-PIE databases, respectively. [ABSTRACT FROM AUTHOR]