An electronic component defect detection method based on SVM. Issue 1 (July 2021)

• Record Type: Journal Article
• Authors: Zhang, Poxi; Qian, Weiqi; Cai, Hongbin; Lu, Guanghui
• Is Part Of: Journal of physics. Volume 1982:Issue 1(2021)
• Publication Date: 2021-07
• Subjects: Defect detection -- Image recognition -- Support vector machines -- Image process -- Machine learning; Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1982/1/012109
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: In the production process of electronic components such as capacitors, bubble defects will occur inside the devices, which will lead to the loss of the functions of electronic components. Traditional methods for detecting bubble defects have many problems, such as low efficiency and low accuracy. Aiming at the bubble defects of the existing electronic components, an SVM-based detection method was proposed, which combined machine learning and image processing to complete the automatic detection of the bubble defects of electronic components. By using the feedback method, the error results obtained from the model classification are added to the training sample set, so that the problems of insufficient sample quantity and incorrect sample classification are solved. The accuracy of the proposed method was verified by capacitor component samples. The accuracy rate was 98.95%, the emission rate was 0.12%, and the error rate was 0.93%. It can be seen that the method proposed in this paper has a good effect on the defect detection of electronic components with the capacitor as an example.