基于自编码器图像重构的织物瑕疵检测算法

doi:10.3969/j.issn.1006-2475.2019.01.006

摘要/Abstract

摘要： 针对含周期图案织物瑕疵检测通常要计算周期，而这又不适应纯色织物，本文提出适应2类织物的检测方法。首先设定检测块大小，按其在无瑕疵图像中随机提取图像块，并训练自编码器。然后将待检图像按设定大小分块，用自编码器重构，并计算重构前后的均方误差。最后对计算结果进行异常值检测，均方误差值偏大的为瑕疵块。实验表明，本文算法适应2类织物，容易实现，检测效果较好。

关键词: 分块, 自编码器, 均方误差, 瑕疵检测

Abstract: The fabric defect detection with periodic pattern generally needs to calculate period, which is not suitable for pure texture fabric. In this paper, the detection method for two kinds of fabric is proposed. Firstly, the size of detect block is set, the image block is extracted randomly from non-defect images, and then the auto-encoder is trained. Secondly, according to the size, the test images are divided into several blocks, and reconstructed with the auto-encoder, and then the mean square errors are computed between the reconstructed result and original data. Lastly, outliers of computing results of test images are detected. With rather large mean square errors value, the blocks are defect blocks. The experiments show that the proposed method is suitable for two kinds of fabric, the process is more practical and the detection results are better.

Key words: partitioning, auto-encoder, mean square error, defect detection

中图分类号:

TP919.8

欧庆芳,谢伙生. 基于自编码器图像重构的织物瑕疵检测算法[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2019.01.006.

OU Qing-fang, XIE Huo-sheng. Fabric Defect Detection Based on Image Reconstruction with Auto-encoder[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2019.01.006.

参考文献

［1］ HANBAY K, TALU M F, ZGVEN  F. Fabric defect detection systems and methods-A systematic literature review［J］. Optik-international Journal for Light and Electron Optics, 2016,127(4):11960-11973.
［2］ NGAN H Y T, PANG G K H , YUNG N H C. Automated fabric defect detection-A review［J］. Image & Vision Computing, 2011,29(7):442-458.
［3］吴哲,刘孝星,郑力新,等. 基于灰度共生矩阵特征图像的织物疵点检测方法［J］. 微型机与应用, 2015,34(21):47-50.
［4］王文杰,强赞霞. 数学形态学在织物疵点检测中的应用［J］. 中原工学院学报, 2010,21(2):28-30.
［5］ YE Y. Fabric defect detection using fuzzy inductive reasoning based on image histogram statistic variables［C］// Proceedings of the 6th International Conference on Fuzzy Systems and Knowledge Discovery. 2009:191-194.
［6］ CHAN C H, PANG G K H. Fabric defect detection by Fourier analysis［J］. IEEE Transactions on Industry Applications, 2002,36(5):1267-1276.
［7］崔玲玲,卢朝阳,李静，等. 基于小波多尺度积与形态学的织物瑕疵检测算法［J］. 光电工程， 2011,38(8):90-95.
［8］ JING J F, FAN X T, LI P F. Automated fabric defect detection based on multiple Gabor filters and KPCA［J］. International Journal of Multimedia & Ubiquitous Engineering, 2016,11(6):93-106.
［9］ ALATA O, RAMANANJARASOA C. Unsupervised textured image segmentation using 2-D quarter plane autoregressive model with four prediction supports［J］. Pattern Recognition Letters, 2005,26(8):1069-1081.
［10］刘威,常兴治,梁久祯,等. 基于局部最优分析的纺织品瑕疵检测方法［J］. 模式识别与人工智能, 2018,31(2):182-189.
［11］WEIMER D, THAMER H, SCHOLZ-REITER B. Learning defect classifiers for textured surfaces using neural networks and statistical feature representations［J］. Procedia CIRP, 2013,7(12):347-352.
［12］LI Y D, ZHAO W G, PAN J H. Deformable patterned fabric defect detection with fisher criterion-based deep learning［J］. IEEE Transactions on Automation Science & Engineering, 2017,14(2):1256-1264.
［13］NGAN H Y T, PANG G K H, YUNG S P, et al. Wavelet based methods on patterned fabric defect detection［J］. Pattern Recognition, 2005, 38(4):559-576.
［14］NGAN H Y T, PANG G K H. Novel method for patterned fabric inspection using Bollinger bands［J］. Optical Engineering, 2006,45(8):187-202.
［15］NGAN H Y T, PANG G K H. Regularity analysis for patterned texture inspection［J］. IEEE Transactions on Automation Science and Engineering, 2009,6(1):131-144.
［16］NG M K, NGAN H Y T, YUAN X M, et al. Patterned fabric inspection and visualization by the method of image decomposition［J］. IEEE Transactions on Automation Science and Engineering, 2014,11(3):943-947.
［17］TSANG C S C, NGAN H Y T, PANG G K H. Fabric inspection based on the ELO rating method［J］. Pattern Recognition, 2016,51(4):378-394.
［18］梁久祯,顾程熙,常兴治. 基于相似关系的纺织品瑕疵检测方法［J］.模式识别与人工智能, 2017,30(5):456-464.
［19］吴宁. 基于纹理边缘周期性与局部方向性的织物疵点检测［J］. 计算机与现代化, 2014(4):16-19.
［20］景军锋,党永强,苏泽斌,等. 基于改进SAE网络的织物疵点检测算法［J］. 电子测量与仪器学报, 2017,31(8):1321-1329.
［21］GOODFELLOW I, BENGIO Y, COURVILLE A. Deep Learning［EB/OL］. ［2018-04-18］. http://www.deeplearningbook.org/contents/autoencoders.html.
［22］曲建岭,杜辰飞,邸亚洲，等. 深度自动编码器的研究与展望［J］. 计算机与现代化, 2014(8):128-134.
［23］曲之琳,胡晓飞. 基于改进激活函数的卷积神经网络研究［J］. 计算机技术与发展, 2017,27(12):77-80.

[1]	唐诗琪, 周瑞平, 谢仕斌, 刘梦赤, 肖文, . 基于栈式降噪编码器的跨语言多标签情感分类[J]. 计算机与现代化, 2023, 0(11): 6-12.
[2]	刘路瑶, 韩培胜. 基于堆叠降噪自编码器的跨项目软件缺陷数量预测方法[J]. 计算机与现代化, 2023, 0(04): 32-38.
[3]	宋晓丽, 张勇波, 张培颖. 基于半监督学习的学生消费数据异常检测[J]. 计算机与现代化, 2022, 0(12): 13-17.
[4]	杨娟, 滕飞, 郭大林. 多模态融合的特征提取方法在SA检测中的应用[J]. 计算机与现代化, 2022, 0(10): 121-126.
[5]	任秋霖, 任德均, 李鑫, 闫宗一, 曹林杰, 唐洪. 基于卷积自编码器的医用玻璃瓶口缺陷检测方法[J]. 计算机与现代化, 2022, 0(08): 114-120.
[6]	张允耀, 黄鹤鸣, 张会云, . 复杂噪声环境下语音识别研究[J]. 计算机与现代化, 2021, 0(09): 68-74.
[7]	陆小敏, 刘凡, 蔡丽华, 李雪丁, 徐啸. 集成栈式自编码器与XGBoost的深度学习海浪有效波高预报模型[J]. 计算机与现代化, 2021, 0(04): 32-36.
[8]	谭晓刚, 戴天喆, 董树林, 张艺鉴, 任敏华. 一种联合盲均衡算法[J]. 计算机与现代化, 2021, 0(02): 89-93.
[9]	王玮1,2. 基于VAE-DBN双模型的智能文本分类方法[J]. 计算机与现代化, 2018, 0(12): 77-.
[10]	张文翔. 基于地理邻近性的自编码器在地点推荐中的应用[J]. 计算机与现代化, 2018, 0(04): 74-.
[11]	范新南,吴晶晶,史朋飞,张学武. 基于劳伦茨信息值的水下大坝裂缝提取算法[J]. 计算机与现代化, 2018, 0(03): 73-.
[12]	朱海洋1，徐根玖2，李元晨1，张梦祺2. 基于图像分块的局部区域动态阈值选取方法[J]. 计算机与现代化, 2016, 0(11): 53-57.
[13]	罗永莲，赵昌垣，贾玉芳，芦彩林. 基于朴素贝叶斯Web新闻内容的抽取方法[J]. 计算机与现代化, 2016, 0(1): 59-63,68.
[14]	刘继承1，王敏莹1，李浩然2. 基于改进CoSaMP算法的图像重建[J]. 计算机与现代化, 2015, 0(5): 48-52.
[15]	黄可望1，冯宗越2,3，朱嘉钢2,3. 基于NIB2DPCA的彩色图像过完整分块特征抽取方法[J]. 计算机与现代化, 2015, 0(12): 78-.