An Adaptive Deep Learning Framework for Fast Recognition of Integrated Circuit Markings
| Autor: | Tangfan Xiahou, Zhang Changhua, Chen Zhongshu, Lin Zuo, Yu Liu |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
business.product_category
business.industry Character (computing) Computer science Orientation (computer vision) Deep learning Integrated circuit Chip Convolutional neural network Computer Science Applications law.invention Set (abstract data type) Control and Systems Engineering law Laptop Computer vision Artificial intelligence Electrical and Electronic Engineering business Information Systems |
| Zdroj: | IEEE Transactions on Industrial Informatics. 18:2486-2496 |
| ISSN: | 1941-0050 1551-3203 |
| Popis: | Fast recognition of integrated circuits markings is an essential but challenging task in electronic device manufacturing lines. This article develops an adaptive deep learning framework to facilitate the fast marking recognition of IC chips. The proposed framework contains four deep learning components, namely chip segmentation, orientation correction, character extraction, and character recognition. The four components utilize different convolutional neural network structures to guarantee excellent adaptivity to a wide range of IC types, and mitigate the influence of the low-quality chip images. In particular, the character extraction model is comprised of two improved label generation strategies and a proposed border correction method, so as to accommodate tiny scale chips and compactly printed markings. Experiments for a set of chip images from a real laptop manufacturing line demonstrate the superiority of the proposed framework to the state-of-the-art models and the effectiveness of handling a great diversity of chips. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|