Improving the performance of machine learning based face recognition algorithm with Multiple Weighted Facial Attribute Sets

Recognizing a face based on its attributes is an easy task for a human to perform; it is nearly automatic, and requires little mental effort. A computer, on the other hand, has no innate ability to recognize a face or facial features, and must be programmed with an algorithm to do so. Generally, to recognize a face, different kinds of the facial features were used separately or in a combined manner. Feature fusion methods and parallel methods performed by integrating multiple feature sets at different levels. However, these feature fusion methods as well as parallel methods do not guarantee better result. Several Feature extraction techniques and fusion models were explored in several earlier works. This work, addresses feature fusion model with multiple weighted facial attribute set. For facial feature set creation, 1. PCA based Eigen feature extraction technique, 2. DCT based feature extraction technique, 3. Histogram Based Feature Extraction technique and 4. Simple intensity based feature Extraction were used. The proposed model has been tested on face images which differ in expression and illumination condition with a dataset obtained from face image databases of ORL. A more significant improvement in term of accuracy was achieved and more significant results were arrived.