Comprehensive Infrared Image Edge detection Algorithm

International Journal of Image Processing

Abhishek Gudipalli¹  Ramashri Tirumala¹ 

[1] $$

关键词: Edge Detection;    Color Models;    Evaluation Metrics;   

DOI  :  

来源: Computer Science Journals

【 摘 要 】

Edge detection is one of the most powerful image analysis tools for enhancing and detecting edges. Indeed, identifying and localizing edges are a low level task in a variety of applications such as 3-D reconstruction, shape recognition, image compression, enhancement, and restoration. This paper introduces a new algorithm for detecting edges based on color space models. In this RGB image is taken as an input image and transforming the RGB image to color models such as YUV, YCbCr and XYZ. The edges have been detected for each component in color models separately and compared with the original image of that particular model. In order to measure the quality assessment between images, SSIM (Structural Similarity Index Method) and VIF (Visual Information Fidelity) has been calculated. The results have shown that XYZ color model is having high SSIM value and VIF value. In the previous papers, edge detection based on RGB color model has low SSIM and VIF values. So by converting the images into different color models shows a significant improvement in detection of edges.Keywords: Edge detection, Color models, SSIM, VIF.

【 授权许可】

Unknown