This study developed a defect-detecting system for automotive wheel nuts. We proposed an image processing method using OpenCV for efficient defect-detection of automotive wheel nuts. Image processing method focused on noise removal, ratio adjustment, binarization, polar coordinate system formation, and orthogonal coordinate system conversion. Through data collection, preprocessing, object detection model training, and testing, we established a system capable of accurately classifying defects and tracking their positions. There are four defect types. Types 1 and 2 defects are defects of products where the product is completely broken circumferentially. Types 3 and 4 defects are defects are small circumferential dents and scratches in the product. We utilized Faster R-CNN and YOLOv8 models to detect defect types. By employing effective preprocessing and post-processing steps, we enhanced the accuracy. In the case of Fast RCNN, AP values were 0.92, 0.93, 0.76, and 0.49 for types 1, 2, 3, and 4 defects, respectively. The mAP was 0.77. In the case of YOLOv8, AP values were 0.78, 0.96, 0.8, and 0.51 for types for types 1, 2, 3, and 4 defects, respectively. The mAP was 0.76. These results could contribute to defect detection and quality improvement in the automotive manufacturing sector.
Citations
Citations to this article as recorded by
Large-area Inspection Method for Machined Micro Hole Dimension Measurement Using Deep Learning in Silicon Cathodes Jonghyeok Chae, Dongkyu Lee, Seunghun Oh, Yoojeong Noh Journal of the Korean Society for Precision Engineering.2025; 42(2): 139. CrossRef
Bone plates are a medical device used for fixing broken bones, which should not have a crack and hole defect. Defect detection is very important because bone plate defect is very dangerous. In this study, we proposed a defect detection model based on a parallel type convolution neural network for detecting bone plate crack and pore deformation. All size filters were different according to the defect shape. A convolution neural network detected pore defects. Another convolution neural network detected the crack. Two convolution neural networks simultaneously detected different defect types. The performance of the defect detection model was measured and used for the F1- score. We confirmed that performance of the defect detection model was 98.4%. We confirmed that the defect detection time was 0.21 seconds.
This paper presents a machine vision-based surface inspection system for journal bearings. Traditionally, human operator inspection classifies the defective and defect-free bearings. Although the operator has capability to find a defect on the bearing surface, his/her inspection ability is influenced by fatigue and physical conditions related to repetitive work. Therefore, machine vision systems are widely used for quality control in order to reduce costs and to improve product quality. In this paper, we develop a machine vision system for journal bearing surface inspection that can inspect various types of defects on the bearing surface, such as laser marking quality, gas pockets, 2 Φ hole measurements, rust and so on. The proposed system was evaluated and installed on a journal bearing manufacturing line. The journal bearing manufacturer reported that the proposed system has high accuracy and efficiency.
Citations
Citations to this article as recorded by
Development of Vision System for Quality Inspection of Machined Holes of Automobile Mechanical Parts Min Yong Han, Ki Hyun Kim, Hyo Young Kim, Kwang In Ko, Kyo Mun Ku, Dong Ju Ki, Jae Hong Shim Journal of the Korean Society for Precision Engineering.2023; 40(6): 499. CrossRef
Image Data-based Product Classification and Defect Detection Hye-Jin Lee, Do-Gyeong Yuk, Jung Woo Sohn Transactions of the Korean Society for Noise and Vibration Engineering.2022; 32(6): 601. CrossRef
Specular highlight region restoration using image clustering and inpainting Hosun Kang, Dokyung Hwang, Jangmyung Lee Journal of Visual Communication and Image Representation.2021; 77: 103106. CrossRef
Modified ORB-SLAM Algorithm for Precise Indoor Navigation of a Mobile Robot Yongjin Ock, Hosun Kang, Jangmyung Lee Journal of Korea Robotics Society.2020; 15(3): 205. CrossRef
Real-time Reflection Light Detection Algorithm using Pixel Clustering Data Dokyung Hwang, Jongwoo An, Hosun Kang, Jangmyung Lee Journal of Korea Robotics Society.2019; 14(4): 301. CrossRef
The automated inspection method of paper cups by using a deep learning classifier is proposed. Unlike conventional inspection methods requiring defect detection, feature extraction, and classification stages, the proposed method gives a unified inspection approach where three separate stages are replaced by one deep-learning model. The images of paper cups are grabbed using a CCD (Charge Coupled Device) camera and diffused LED lights. The defect patches are extracted from the gathered images and then augmented to be trained by the deep- learning classifier. The random rotation, width and height shift, horizontal and vertical flip, shearing, and zooming are used as data augmentation. Negative patches are randomly extracted and augmented from gathered images. The VGG (Visual Geometry Group)-like classifier is used as our deep-learning classifier and has five convolutional layers and max-pooling layers for every two convolutional layers. The drop-outs are adopted to prevent overfitting. In the paper, we have tested four kinds of defects and nondefects. The optimal classifier model was obtained from train and validation data and the model shows 96.5% accuracy for test data. The results conclude that the proposed method is an effective and promising approach for paper cup inspection.
Citations
Citations to this article as recorded by
Research and Evaluation on an Optical Automatic Detection System for the Defects of the Manufactured Paper Cups Ping Wang, Yang-Han Lee, Hsien-Wei Tseng, Cheng-Fu Yang Sensors.2023; 23(3): 1452. CrossRef
Method and Installation for Efficient Automatic Defect Inspection of Manufactured Paper Bowls Shaoyong Yu, Yang-Han Lee, Cheng-Wen Chen, Peng Gao, Zhigang Xu, Shunyi Chen, Cheng-Fu Yang Photonics.2023; 10(6): 686. CrossRef
First
Prev
