Surface Defect Detection and Classification Based on Statistical Filter and Decision Tree

Abstract

Abstract-Industrial quality inspection is a major issue due to the growing of market competitiveness which requires the product to be checked in terms of online defect detection. Meanwhile, labor inspection has been eliminated due to its limitation that restricts the speed of manufacturing process. Hence, automated inspection process is inevitable to preserve the industrial health and lift human function into management tasks. There are huge efforts on Automated Visual Inspection (AVI) research area, particularly in plain surfaces such as ceramics and fabrics. The inspection modeling includes statistical-based, model-based and color analysis. Most systems are well studied and tested on Charge-Coupled Device (CCD) image sensor. However, only few approaches are carried out for Complementary Metal Oxide Semiconductor (CMOS) imaging modality. This study presents an inspection scheme to detect defect in plain fabric based on statistical filter and geometrical features on CMOS-based image input. The advantage of this technology is obvious regarding to its affordable development especially for small and medium industries. We showed that it is suitable for defect inspection applications that does not require specialized lighting environment. In addition, a classification approach is developed based on decision tree framework. The result for static image shows the classification achieve 99% accuracy.

Defect Detection Method of Phosphor in Glass Based on Improved YOLO5 Algorithm

“…Compared with traditional defect detection methods, defect detection based on deep learning trains the model through convolutional neural networks and uses the trained model to detect defects. This approach is more efficient compared to traditional methods, offering improved calculation speed and recognition accuracy [7]. According to the model training method, it can be divided into two types: one-stage detection algorithms and two-stage detection algorithm [8].…”

Automatic classification of refrigerator using doubly convolutional neural network with jointly optimized classification loss and similarity loss

“…Various vision-based applications in refrigerator manufacturing process have been brought forward along with the development of industrial automation especially in the emergence of industry 4.0 standardization [2][3][4]. As an example, automatic classification is potentially invaluable Experimental results show that the CNN-based methods outperform the state-of-the-art SVM-based methods with handcrafted features.…”