https://scholars.lib.ntu.edu.tw/handle/123456789/581296
標題: | TsanKit: artificial intelligence for solder ball head-in-pillow defect inspection | 作者: | Tsan T.-C Shih T.-F CHIOU-SHANN FUH |
關鍵字: | 3D modeling; Convolutional neural networks; Deep learning; Defects; Image recognition; Inspection; Learning systems; Software testing; Soldering; Support vector machines; Defect inspection; Inspection methods; Inspection process; Inspection software; Intermittent failure; Machine vision algorithm; Over fitting problem; State of the art; Learning algorithms | 公開日期: | 2021 | 卷: | 32 | 期: | 3 | 來源出版物: | Machine Vision and Applications | 摘要: | In this paper, we propose an AI (Artificial Intelligence) solution for solder ball HIP (Head-In-Pillow) defect inspection. The HIP defect will affect the conductivity of the solder balls leading to intermittent failures. Due to the variable location and shape of the HIP defect, traditional machine vision algorithms cannot solve the problem completely. In recent years, Convolutional Neural Network (CNN) has an outstanding performance in image recognition and classification, but it is easy to cause overfitting problems due to insufficient data. Therefore, we combine CNN and the machine learning algorithm Support Vector Machine (SVM) to design our inspection process. Referring to the advantages of several state-of-the-art models, we propose our 3D CNN model and adopt focal loss as well as triplet loss to solve the data imbalance problem caused by rare defective data. Our inspection method has the best performance and fast testing speed compared with several classic CNN models and the deep learning inspection software SuaKIT. ? 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85103352776&doi=10.1007%2fs00138-021-01192-8&partnerID=40&md5=6833a29b53810da2ffcc658be48b1423 https://scholars.lib.ntu.edu.tw/handle/123456789/581296 |
ISSN: | 09328092 | DOI: | 10.1007/s00138-021-01192-8 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。