Vision-Based Nut Quality Classification Using Conditional GAN and CNN

• Published in: IEEE transactions on automation science and engineering 2025-01, p.1-1
• Main Authors: Hung, Kuei-Jung, Lee, Tzu-Chen, Wang, Chiao-Sheng, Lin, Tsung-Chun, Guo, Chen-Wei Conan, Tsay, Der-Min, Perng, Jau-Woei
• Format: Article
• Language: English
• Subjects: Classification algorithms; conditional generative adversarial network; Convolutional neural networks; deep learning; Fasteners; Feature extraction; Inspection; Instruction sets; internal thread of nut; Machine learning; Measurement by laser beam; Message systems; nut quality classification; Torque
• ISSN: 1545-5955; 1558-3783
• DOI: 10.1109/TASE.2025.3533013

In this study, the quality of a nut is discussed by considering images of the internal thread, and an analysis is conducted using traditional machine-learning and deep-learning algorithms. Compared to the traditional contact methods, the vision-based method has the advantage of fast computing speed and is not affected by the conditions of tapping speed. The pitch and pitch diameter of the internal thread are the indicators that characterize nut quality classification. For one nut, 36 internal thread images are collected, one image per 10 degrees, by the self-designed laser triangulation measurement platform. Using the laser triangulation method, the information on both indicators can be obtained and analyzed. In the traditional machine-learning methods, the internal thread images undergo several preprocessing procedures to obtain the region of interest and calculate the depth between the crest and root. Subsequently, 33 handcrafted features are used to extract the features from the 36 processed images. Finally, the features are classified by three families of machine-learning algorithms, including support vector machines, k-nearest neighbors, and decision trees. In the deep-learning method, conditional generative adversarial network and convolutional neural network (CNN) are used for data augmentation and nut quality classification, respectively. The experimental results show that the proposed CNN model can achieve a higher classification accuracy rate. Furthermore, the proposed CNN model trained with the generated images is better equipped to detect the nut quality under different decision thresholds.