Hybrid Colour Infrared Image Edge detection using RGB-YCbCr image Fusio

Abstract

Edges are one of the most important features in images and their analysis and detection in computer vision and image processing is an essential goal. Indeed, a variety of applications such as 3-D reconstruction, shape recognition, image compression, enhancement, and restoration identifying and localizing edges are a low level tasks. This paper presents a Hybrid approach to Infrared image edge detection which becomes a vital point in pattern recognition. The acquired image which is in RGB colour space by satellite are near infrared images which can be used as subject of interest based on the radiation. Edge detection becomes a bottleneck for infrared images as it constitutes with lesser properties in terms of color. A hybrid edge detection algorithm is required to accomplish a better edge detection. Two algorithms are proposed in this process, Firs the edge detection is done in RGB colour space and the significant features extracted are fused. The second method proposed is based on YCbCr image edge detection and fusing the Luminance and R component of the image which shows better edge detection results.