Open AccessUsing Haar-like Features and SVM Classifier for Quality Assurance in a Surgical Mask Production Line
Author(s) -
Laszlo Marak
Publication year - 2021
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v10i2.31636
Subject(s) - computer science , preprocessor , quality assurance , production line , artificial intelligence , support vector machine , feature selection , pattern recognition (psychology) , redundancy (engineering) , classifier (uml) , feature (linguistics) , computer vision , engineering , operations management , mechanical engineering , linguistics , philosophy , external quality assessment , operating system
With the recent increase for demand of surgical masks, the design and development of mask production lines has become an ever pressing issue. These production lines produce low cost high quantity products. As there are errors during the production, it is important to be able to detect invalid masks to assure that the produced masks are of consistent quality. Manual quality assurance using human operators is an error prone and a costly solution. In this article we describe an image classification method, which is using a low-cost Commercial Camera System and relies on Haar-like features combined with Maximum Relevance, Minimum Redundancy feature selection to detect the invalid masks at the end of the production process. The classification method consists of Preprocessing, Feature Selection and SVM Training. We have tested the method on a database of 150 000 images and it provides a high accuracy method which we use in the Production Line.