Loading [MathJax]/extensions/MathMenu.js
Improved Image Processing Algorithm for Quality Test on a Flexible Manufacturing Mechatronic Line | IEEE Conference Publication | IEEE Xplore

Improved Image Processing Algorithm for Quality Test on a Flexible Manufacturing Mechatronic Line


Abstract:

This article proposes a new approach for image processing algorithms based on image processing techniques: image filtering using the Gaussian smoothing filter, edge detec...Show More

Abstract:

This article proposes a new approach for image processing algorithms based on image processing techniques: image filtering using the Gaussian smoothing filter, edge detection, normal cross correlation (NCC) and M-estimator Sample Consensus (MASC). The new algorithm increases the accuracy of the detection function, but also the duration of the quality analysis operation. The image analysis is performed by recursively searching for a "template image" considered to be the landmark image. Cyclic searches involve performing two analysis steps: an identification of the edges of the template image and an analysis of the area content of the identified surface. Following this recursive analysis and considering a certain predefined search error, the algorithm decides if the analysed image has any defects. In the end, the aims of this research are to optimize the industrial quality test (QT) function and the implementation in the QT station on a high- performance mechatronic system for flexible assembly with component recovery. Related on QT result, the manufacturing flow of assembly can continue with disassembly and recovery operations, or transport and storage of good products. The results presented in this article will be used in future research for design and implementation of a Machine Vision system.
Date of Conference: 08-10 October 2020
Date Added to IEEE Xplore: 23 November 2020
ISBN Information:
Print on Demand(PoD) ISSN: 2372-1618
Conference Location: Sinaia, Romania

References

References is not available for this document.