ANALYSIS AND COMPARISON OF CRACK DETECTION IN METAL IMAGES USING BILATERAL FILTER AND DIFFUSION TECHNIQUE

Abstract

The streak image caused by metal implants degrades the image quality and limits the applications of metal that results in loss of image quality. The proposed method uses bilateral filter and it is compared with diffusion technique and fractional wavelet transformation to extract the texture features. Diffusion method used in this previous work is inefficient for detecting the pitting and laminating defects. By using Gradient Magnitude and structure coherence, the exact level of defect is found. For this purpose, an automatic defect detection and classification technique using enhanced bilateral filter is proposed to ensure the better quality of metal in manufacturing process as well as production rate. In this proposed methodology for crack detection in metal images, bilateral filter method is used to acquire the knowledge about the pattern of defects within a very short period of time and so that the defected metal may not be mixed with the fresh metal.