• Sumit Bagal
• Chetan Dubal
• Shubham Mali
• Tejas Mahajan

The shape recognition and defect detection of defects at the early stage will helps smooth production process, saves production cost and time. This paper presents a computationally efficient 2D computer vision-based approach to recognize machine parts and detect damaged parts on the assembly line. A contour of the machine parts is extracted and normalized by an equal part area method to describe the shape. The defects in the machine part such as damage, cracks are identified by the similarity measure between model shape and the data extracted from machine part of the assembly line. It gives important clues for machine part shape recognition and defect identification. Surface defects are a major reason for poor quality of parts for manufacturers. Inspection processes done in industries are mostly manual and time consuming. To reduce error on identifying surface defects requires more automotive and accurate inspection process. Considering this lacking, the recognizer identifies the surface defects within economical cost and produces less error prone inspection system in real time. This research implements a surface Defect Recognizer which uses computer vision methodology with the combination of local thresholding to identify possible defects. Under the complex background of image acquisition, a new model faster r-CNN with Tensor Flow is proposed for online detection of surface defects. It has better recognition of microdefects under a complex background than some other recognition networks.

Computer Vision, Object Detection, Tensor flow, Faster R-CNN

"SURFACE DEFECT DETECTION THROUGH COMPUTER VISION ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 6, page no.d189-d194, June-2022, Available :http://www.jetir.org/papers/JETIR2206324.pdf

"SURFACE DEFECT DETECTION THROUGH COMPUTER VISION ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 6, page no. ppd189-d194, June-2022, Available at : http://www.jetir.org/papers/JETIR2206324.pdf