Title: Emery particles identification under contour extraction with maximum entropy approaches

Authors: Peiyi Zhu; Ying Ding; Ya Gu

Addresses: School of Electrical and Automatic Engineering, Changshu Institute of Technology, 99 Hu Shan Lu, Changshu, Suzhou, Jiangsu, 215556, China ' School of Electrical and Automatic Engineering, Changshu Institute of Technology, 99 Hu Shan Lu, Changshu, Suzhou, Jiangsu, 215556, China ' School of Electrical and Automatic Engineering, Changshu Institute of Technology, 99 Hu Shan Lu, Changshu, Suzhou, Jiangsu, 215556, China

Abstract: The emery line is kind of cutting line electroplated with emery particles, which is used to cut hard material such as a silicon wafer, etc. The emery line cutting capacity depends on the number, size and density of emery particles on the line. Traditional detecting by workers is replaced by the technology of machine vision, which can improve efficiency of detecting and avoid resources be wasted. However, the emery particles identification is difficult for the adhesive particles on the cutting line using existing methods. The method of contour extraction with maximum entropy approaches is proposed. Image binarization is adopted with maximum entropy threshold method. The initial evolution of the level set curve is present to process the outline of an image which can simplify the process of evolution from the initial curve to emery particles contour. Adaptive weight coefficient is used only for adaptively evolving according to the picture information, which can improve the adaptability of model identification. Experimental results show that the proposed algorithm has higher accuracy in terms of emery particles identification compared with the threshold segmentation algorithm and the traditional level set algorithm.

Keywords: emery particles; contour extraction; maximum entropy threshold method; edge detection; level set.

DOI: 10.1504/IJMIC.2021.122469

International Journal of Modelling, Identification and Control, 2021 Vol.38 No.1, pp.81 - 87

Received: 11 Feb 2021
Accepted: 23 Mar 2021

Published online: 04 Apr 2022 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article