期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2013
卷号：4
期号：6
页码：945-949
出版社：TechScience Publications
摘要：Face recognition is the broad area of researchers for exploring new techniques. The main part of the face recognition is feature extraction. Feature extraction is the form of dimensionality reduction. When the input data to an algorithm is too large to be processed then the input data will be transformed into a reduced representation set of features. Transforming the input data into the set of features is called feature extraction. For the feature extraction and image processing we use rectangular feature. The rectangular feature is the techniques where we have consider pixel values of the gray scale image. In the rectangular feature xmin, ymin, height and width are considering for calculation the pixel values on particular point in an image. We have to calculate face feature vector using principal component analysis (PCA). We have taken three features eyes, lips and nose for feature extraction these features are used for face recognition. On these four rectangular features we have to applied PCA algorithm for dimensionality reduction then feature vectors used for classifier. Then we have to train RBFNN (radial basis function neural network) for classifying the output. Result comes in the form of recognition rate.
关键词：Face detection; Face recognition; Image processing;Machine learning and Rectangular feature
