Revisiting the Performance of PCA Versus FDA Versus Simple Projection for Image Recognition

Abstract

Computer vision becomes a great area of research due to the huge availability of images and videos. For enhancement of security, biomedical imaging, or automation of identification, one may need useful tools to recognize images. One main problem of image data set is high dimensional, and it is very expensive to work with huge dimensions. In this paper, our main aim is to show a better dimension reduction process of high dimensional image data sets from several existing techniques. To verify it we start with most useful singular value decomposition to reduce the dimensionality of data to incorporate principal components. On the other hand, we classify data in advance to work out Fisher’s discriminant. From many real-world examples, we set a very well-known paradigm of analysis using Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) or Fisher Discriminant Analysis (FDA) and Simple Projection (SP) to recognize people from their facial images. We consider that we have some images of known people that can be used to compare and recognize new images (of the same set of face images). Moreover, we show graphical and tabular representation for average performance of correct recognition as well as analyze the effectiveness of three different machine learning techniques.