The Study and Literature Review of a Feature Extraction Mechanism in Computer Vison

Abstract

Detecting the Features in the image is a challenging task in computer vison and numerous image processing applications. For example to detect the corners in an image there exists numerous algorithms. Corners are formed by combining multiple edges and which sometimes may not define the boundary of an image. This paper is mainly concentrates on the study of the Harris corner detection algorithm which accurately detects the corners exists in the image. The Harris corner detector is a widely used interest point detector due to strong features such as rotation, scale, illumination and in the case of noise. It is based on the local auto-correlation function of a signal; where the local auto-correlation function measures the local changes of the signal with patches shifted by a small amount in di?erent directions. In out experiments we have shown the results for gray scale images as well as for color images which gives the results for the individual regions present in the image. This algorithm is more reliable than the conventional methods.