改进YOLOv8的轻量级瓷砖表面缺陷检测

doi:10.3778/j.issn.1002-8331.2312-0155

摘要/Abstract

摘要： 在瓷砖表面缺陷检测方面，在保证一定检测速度的前提下，对于小目标缺陷的检测较为困难，总体检测精度依然较低。提出了一种改进YOLOv8的瓷砖表面缺陷检测方法。第一，对原始的大幅面瓷砖数据集进行数据预处理，通过切片操作得到适合YOLOv8输入尺寸的瓷砖数据，防止瓷砖缺陷在缩放的过程中丢失；第二，考虑到瓷砖表面存在小目标缺陷的占比较大问题，使用SPD-Conv的结构代替传统的下采样方式，能够完整地保留通道维度中的所有信息，从而提高对小目标缺陷的检测能力；第三，对YOLOv8中原有的C2f模块进行改造，加入了Efficient Channel Attention注意力机制，设计了C2f_ECA模块，并在backbone网络中进行替换，使得网络在特征提取的过程中能够更为关注缺陷信息，减少背景信息的干扰；第四，添加了微小目标检测头在第二次下采样后进行检测，提高YOLOv8对微小目标的检测能力。该方法在天池瓷砖瑕疵检测数据集上进行实验验证，改进后的模型分别在mAP50-95、mAP50和mAP75上达到57.7%、86.6%、60.6%，比基础网络YOLOv8s分别提升了9.4、5、14.3个百分点。同时，高于YOLOv8m的精度和远低于YOLOv8m的复杂度，属于轻量级模型，符合工业化的需求。

关键词: 深度学习, 目标检测, 瓷砖表面缺陷检测, YOLOv8, 注意力机制

Abstract: In terms of tile surface defect detection, under the premise of ensuring a certain detection speed, it is more difficult to detect small target defects, and the overall detection accuracy is still low. This paper proposes an improved tile surface defect detection method for YOLOv8. Firstly, data preprocessing is performed on the original large-format tile dataset, and tile data suitable for the input size of YOLOv8 is obtained through slicing operation to prevent tile defects from being lost in the process of scaling. Secondly, taking into account that there is a large proportion of small target defects on the tile surface, the structure of SPD-Conv is used instead of the traditional downsampling method, which can completely retain all the information in the channel dimension, so as to improve the detection ability of small target defects. Thirdly, the original C2f module in YOLOv8 is modified by adding the efficient channel attention (ECA) mechanism, designing the C2f_ECA module, and replacing it in the backbone network, so that the network can pay more attention to the defect information and reduce the interference of background information in the process of feature extraction Fourthly, the tiny target detection head is added to detect after the second downsampling to improve the detection ability of YOLOv8 on tiny targets. The method is experimentally validated on the Tianchi tile defect detection dataset, and the improved model achieves 57.7%, 86.6%, and 60.6% on mAP50-95, mAP50, and mAP75, respectively, which are 9.4, 5, and 14.3 percentage points higher than the base network YOLOv8s, respectively. Meanwhile, there are higher accuracy and much lower complexity than YOLOv8m, which is a lightweight model and meets the needs of industrialization.

Key words: deep learning, target detection, surface defect detection of ceramic tiles, YOLOv8, attention mechanism

余松森, 薛国鹏, 何皇, 赵桂, 文火生. 改进YOLOv8的轻量级瓷砖表面缺陷检测[J]. 计算机工程与应用, 2024, 60(18): 88-102.

YU Songsen, XUE Guopeng, HE Huang, ZHAO Gui, WEN Huosheng. Lightweight Detection of Ceramic Tile Surface Defects on Improved YOLOv8[J]. Computer Engineering and Applications, 2024, 60(18): 88-102.

参考文献

[1] GAO X, JIAN M, HU M, et al. Faster multi-defect detection system in shield tunnel using combination of FCN and faster RCNN[J]. Advances in Structural Engineering, 2019, 22(13): 2907-2921.
[2] HU B, ZHOU D, WU Q, et al. An improved defect detection algorithm for industrial products via lightweight convolutional neural network[C]//Proceedings of the 6th International Conference on Advances in Image Processing, 2022: 13-19.
[3] ZHU Z, ZHU P, ZENG J, et al. A surface fatal defect detection method for magnetic tiles based on semantic segmentation and object detection: IEEE ITAIC (ISSN: 2693-2865)[C]//Proceedings of the 2022 IEEE 10th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), 2022: 2580-2586.
[4] LIU K, LI A, WEN X, et al. Steel surface defect detection using GAN and one-class classifier[C]//Proceedings of the 2019 25th International Conference on Automation and Computing (ICAC), 2019: 1-6.
[5] 汪颖, 娄树理. 基于改进Deeplabv3+的瓷砖表面缺陷检测[J]. 烟台大学学报 (自然科学与工程版), 2024(1): 74-80.
WANG Y, LOU S L. Tile surface defect detection based on improved Deeplabv3+[J]. Journal of Yantai University (Natural Science and Engineering Edition), 2024(1): 74-80.
[6] 王淑青, 顿伟超, 黄剑锋, 等. 基于YOLOv5的瓷砖表面缺陷检测[J]. 包装工程, 2022, 43(9): 217-224.
WANG S Q, DUN W C, HUANG J F, et al. Ceramic tile surface defect detection based on YOLOv5[J]. Packaging Engineering, 2022, 43(9): 217-224.
[7] 冯昕宇. 基于改进YOLOv5检测模型的瓷砖表面瑕疵检测[D]. 北京: 北京化工大学, 2022.
FENG X Y. Tile surface defect detection based on improved YOLOv5 detection model[D]. Beijing: Beijing University of Chemical Technology, 2022.
[8] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-788.
[9] REIS D, KUPEC J, HONG J, et al. Real-time flying object detection with YOLOv8[J]. arXiv:2305.09972, 2023.
[10] SUNKARA R, LUO T. No more strided convolutions or pooling: a new CNN building block for low-resolution images and small objects[C]//Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Cham: Springer Nature Switzerland, 2022: 443-459.
[11] BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate[J]. arXiv:1409.0473, 2014.
[12] TONG K, WU Y, ZHOU F. Recent advances in small object detection based on deep learning: a review[J]. Image and Vision Computing, 2020, 97: 103910.
[13] TALAAT F M, ZAINELDIN H. An improved fire detection approach based on YOLO-v8 for smart cities[J]. Neural Computing and Applications, 2023, 35(28): 20939-20954.
[14] YU G, ZHOU X. An improved YOLOv5 crack detection method combined with a bottleneck Transformer[J]. Mathematics, 2023, 11(10): 2377.
[15] QIU L, ZHU W, LI Y, et al. YOLO-based multi-class target detection for SAR images[C]//Proceedings of the 2023 IEEE 7th Information Technology and Mechatronics Engineering Conference (ITOEC), 2023: 1671-1675.
[16] WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020: 390-391.
[17] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016: 770-778.
[18] XU X, JIANG Y, CHEN W, et al. Damo-yolo: a report on real-time object detection design[J]. arXiv:2211.15444, 2022.
[19] FU J, LIU J, TIAN H J, et al. Dual attention network for scene segmentation[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2020: 3141-3149.
[20] MA W, WU Y, CEN F, et al. MDFN: multi-scale deep feature learning network for object detection[J]. Pattern Recognition, 2020, 100: 107149.
[21] ZHANG S, CHI C, YAO Y, et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 9759-9768.
[22] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[23] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 7464-7475.
[24] QI C, GAO J, PEARSON S, et al. Tea chrysanthemum detection under unstructured environments using the TC-YOLO model[J]. Expert Systems with Applications, 2022, 193: 116473.
[25] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 7132-7141.
[26] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV), 2018: 3-19.
[27] ZHANG D, ZHENG Z, LI M, et al. CSART: channel and spatial attention-guided residual learning for real-time object tracking[J]. Neurocomputing, 2021, 436: 260-272.
[28] ROSENBLATT F. The perceptron: a probabilistic model for information storage and organization in the brain[J]. Psychological Review, 1958, 65(6): 386.
[29] XU K, BA J, KIROS R, et al. Show, attend and tell: neural image caption generation with visual attention[C]//International Conference on Machine Learning, 2015: 2048-2057.
[30] ROBBINS H, MONRO S. A stochastic approximation method[J]. The Annals of Mathematical Statistics, 1951: 400-407.
[31] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934, 2020.
[32] TAN M, LE Q. Efficientnet: rethinking model scaling for convolutional neural networks[C]//Proceedings of the International Conference on Machine Learning, 2019: 6105-6114.
[33] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems, 2015.
[34] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision (ECCV 2016), Amsterdam, The Netherlands, October 11-14, 2016. [S.l.]: Springer International Publishing, 2016: 21-37.
[35] REDMON J, FARHADI A. Yolov3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[36] WANG D, HE D. Channel pruned YOLOV5s-based deep learning approach for rapid and accurate apple fruitlet detection before fruit thinning[J]. Biosystems Engineering, 2021, 210: 271-281.
[37] LV W, XU S, ZHAO Y, et al. Detrs beat yolos on real-time object detection[J]. arXiv:2304.08069, 2023.
[38] CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 213-229.
[39] WANG C, HE W, NIE Y, et al. Gold-YOLO: efficient object detector via gather-and-distribute mechanism[J]. arXiv:2309.11331, 2023.