Open AccessDefect Detection of Industrial Products Using Image Segmentation and Saliency
Author(s) -
P. Anantha Prabha,
M. Bharathwaj,
Karthik Dinesh,
G Hari Prashath
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1916/1/012165
Subject(s) - artificial intelligence , computer science , enhanced data rates for gsm evolution , computer vision , process (computing) , segmentation , image processing , edge detection , image (mathematics) , representation (politics) , quality (philosophy) , product (mathematics) , mathematics , philosophy , epistemology , politics , geometry , political science , law , operating system
The manufacturing industries have been searching and developing new solutions to increase the product quality and to decrease the time taken and costs of production. Defect detection methodologies consume much time in manufacturing and manual inspections for quality enhancement. The existing systems cannot handle the data other than the trained ones as they followed the comparison process with the dataset which is of more time consuming and lack of effective depth representation. In the proposed system, multi scale saliency defect detection algorithm is implemented to obtain the boundaries and range of defect in the surface of industrial products. The defect in the products can be detected using pre-processing defect image with color channels, detecting uneven illumination and post processing the defect image thereby splitting out the defect part from original image with edge detection and contours. Hence the output will be of more robust and accurate comparing to the existing systems.