Abstract
With the increasing population, there is a high demand for housing, commercial buildings, and lifestyle facilities. The development of modern manufacturing technology has led to higher quality control requirements for tiles. This article presents a ceramic tile defect detection method based on Faster R-CNN, primarily focused on detecting surface defects or cracks on tiles. The method replaces VGG16 with the ResNet-101 network as a new backbone and utilizes depth-wise separable convolution to address efficiency issues resulting from the backbone replacement. Finally, Soft-NMS is employed to optimize regression boxes and prevent missed detections. Experimental results demonstrate that the improved algorithm achieves a mAP of 70.4%, a 13.2% enhancement over the original algorithm, highlighting the effectiveness and feasibility of the proposed approach.
Publisher
Darcy & Roy Press Co. Ltd.
Reference13 articles.
1. Huang HuiNing. Global Ceramic Tile Development Status and Implications[J].Foshan Ceramics.Vol. 25(2015),p.1-11.
2. SHOCKLETTI.Review on application of surface defect detection[J].Electronic Technology.Vol. 49(2020),p.189-191.
3. Pu YuXiang.Design of Bottle Cap Visual Inspection System Based on Machine Vision[J].Light Textile Industry and Technology. Vol. 49(2020),p.30-33.
4. Yang Cui.Speckled Micro-defects Detection Based on Deep Neural Network Learning[J].Journal of Anqing Normal University(Natural Science Edition).Vol.28(2022)No.4,p.51-56.
5. Biradara M, Shiparamattia B,Patilb B .Fabric Defect Detection Using Deep Convol-utional Neural Network[J].Optical Memory and Neural Networks.Vol. 30(2021),p.250-256