Visual techniques for defects detection in steel products: A comparative study. (April 2022)

• Record Type: Journal Article
• Authors: Mordia, Ravikant; Kumar Verma, Arvind
• Is Part Of: Engineering failure analysis. Volume 134(2022)
• Publication Date: 2022-04
• Subjects: Image processing -- Defect detection -- Feature extraction -- Defect classifications; System failures (Engineering) -- Periodicals; Fracture mechanics -- Periodicals; Reliability (Engineering) -- Periodicals; Pannes -- Périodiques; Rupture, Mécanique de la -- Périodiques; Fiabilité -- Périodiques; Fracture mechanics; Reliability (Engineering); System failures (Engineering); Periodicals; Electronic journals; 620.112
• DOI: 10.1016/j.engfailanal.2022.106047
• Languages: English
• ISSNs: 1350-6307

Abstract

Highlights: There are two categories of steel products: flat products and long products. There are about 55 different types of defects found in steel structures. Hardware setup for the visual defect detection: camera, light selection, lighting methods. Defect detection methods: statistical method, filtering method, model based method, machine learning methods. Defect classifiers: supervised and unsupervised classifiers. Abstract: Non-destructive testing methods for detection of steel surfaces have become very popular to check the quality of surface finish in the steel and iron industries. Vision based approach which uses image processing has advanced with good accuracy for the surface inspection and classifications. This paper presents a review of some techniques based on vision system for detection surface defects. The purpose of this paper is to check the status of research progress in the field of vision inspection system. In this regard, hardware system, software system, lighting method and its selection, image processing and control system have been discussed. Development in vision based defect detection techniques and classifiers for classification of the defects have been presented in this paper.