Surface scratch recognition method based on deep neural network

doi:10.11772/j.issn.1001-9081.2018112247

Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (7): 2103-2108.DOI: 10.11772/j.issn.1001-9081.2018112247

• Virtual reality and multimedia computing • Previous Articles Next Articles

Surface scratch recognition method based on deep neural network

LI Wenjun^1,2, CHEN Bin^2,3, LI Jianming^1,2, QIAN Jide^1,2

1. Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu Sichuan 610041, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China;
3. Guangzhou Electronic Technology Company Limited of Chinese Academy of Sciences, Guangzhou Guangdong 510070, China

Received:2018-11-09 Revised:2019-01-25 Online:2019-07-10 Published:2019-07-15
Supported by:
This work is partially supported by the Major Scientific and Technological Project of Guangdong Province (2017B030306017), the Industry-University-Research Cooperation Project of Guangdong Province (2017B090901040).

基于深度神经网络的表面划痕识别方法

李文俊^1,2, 陈斌^2,3, 李建明^1,2, 钱基德^1,2

1. 中国科学院成都计算机应用研究所, 成都 610041;
2. 中国科学院大学, 北京 100049;
3. 中国科学院广州电子技术有限公司, 广州 510070

通讯作者: 陈斌
作者简介:李文俊(1994-),男,湖南岳阳人,硕士研究生,CCF会员,主要研究方向:计算机视觉、深度学习;陈斌(1970-),男,四川广汉人,研究员,博士生导师,博士,主要研究方向:实时工业图像分析、字符识别、智能视觉控制;李建明(1989-),男,四川南部人,博士研究生,主要研究方向:目标识别、深度学习;钱基德(1988-),男,四川大英人,博士,主要研究方向:机器视觉、深度学习。
基金资助:
广东省重大科技专项（2017B030306017）；广东省产学研合作项目（2017B090901040）。

Abstract

Abstract:

In order to achieve robust, accurate and real-time recognition of surface scratches under complex texture background with uneven brightness, a surface scratch recognition method based on deep neural network was proposed. The deep neural network for surface scratch recognition consisted of a style transfer network and a focus Convolutional Neural Network (CNN). The style transfer network was used to preprocess surface scratches under complex background with uneven brightness. The style transfer networks included a feedforward conversion network and a loss network. Firstly, the style features of uniform brightness template and the perceptual features of the detected image were extracted through the loss network, and the feedforward conversion network was trained offline to obtain the optimal parameter values of network. Then, the images with uniform brightness and uniform style were generated by style transfer network. Finally, the proposed focus convolutional neural network based on focus structure was used to extract and recognize scratch features in the generated image. Taking metal surface with light change as an example, the scratch recognition experiment was carried out. The experimental results show that compared with traditional image processing methods requiring artificial designed features and traditional deep convolutional neural network, the false negative rate of scratch detection is as low as 8.54% with faster convergence speed and smoother convergence curve, and the better detection results can be obtained under different depth models with accuracy increased of about 2%. The style transfer network can retain complete scratch features with the problem of uneven brightness solved, thus improving the accuracy of scratch recognition, while the focus convolutional neural network can achieve robust, accurate and real-time recognition of scratches, which greatly reduces false negative rate and false positive rate of scratches.

Key words: uneven brightness, complex texture background, surface scratch recognition, style transfer network, Convolutional Neural Network (CNN)

摘要：

为实现亮度不均的复杂纹理背景下表面划痕的鲁棒、精确、实时识别，提出一种基于深度神经网络的表面划痕识别方法。用于表面划痕识别的深度神经网络由风格迁移网络和聚焦卷积神经网络（CNN）构成，其中风格迁移网络针对亮度不均的复杂背景下的表面划痕进行预处理，风格迁移网络包括前馈转换网络和损失网络，首先通过损失网络提取亮度均匀模板的风格特征和检测图像的知觉特征，对前馈转换网络进行离线训练，获取网络最优参数值，最终使风格迁移网络生成亮度均匀且风格一致的图像，然后，利用所提出的基于聚焦结构的聚焦卷积神经网络对生成图像中的划痕特征进行提取并识别。以光照变化的金属表面为例，进行划痕识别实验，实验结果表明：与需要人工设计特征的传统图像处理方法及传统深度卷积神经网络相比，划痕漏报率低至8.54%，并且收敛速度更快，收敛曲线更加平滑，在不同的深度模型下均可取得较好的检测效果，准确率提升2%左右。风格迁移网络能够保留完整划痕特征的同时有效解决亮度不均的问题，从而提高划痕识别精度；同时聚焦卷积神经网络能够实现对划痕的鲁棒、精确、实时识别，大幅度降低划痕漏报率和误报率。

关键词: 亮度不均, 复杂纹理背景, 表面划痕识别, 风格迁移网络, 卷积神经网络

CLC Number:

LI Wenjun, CHEN Bin, LI Jianming, QIAN Jide. Surface scratch recognition method based on deep neural network[J]. Journal of Computer Applications, 2019, 39(7): 2103-2108.

李文俊, 陈斌, 李建明, 钱基德. 基于深度神经网络的表面划痕识别方法[J]. 计算机应用, 2019, 39(7): 2103-2108.

References

[1] 宋迪,张东波,刘霞.基于Gabor和纹理抑制的手机配件划痕检测[J].计算机工程,2014,40(9):1-5.(SONG D, ZHANG D B, LIU X. Scratch detection for mobile phone accessories based on Gabor and texture suppression[J]. Computer Engineering, 2014, 40(9):1-5.)
[2] 韩芳芳,段发阶,张宝峰,等.单线阵CCD系统的表面凹坑缺陷检测方法[J].哈尔滨工业大学学报,2012,44(4):116-120.(HAN F F, DUAN F J, ZHANG B F, et al. Study and modeling for surface pit defect detection based on linear array CCD system[J]. Journal of Harbin Institute of Technology, 2012,44(4):116-120.)
[3] 崔炽标,李阳,毛霆,等.基于预处理与卷积神经网络的塑件划痕检测[J].模具工业,2017,43(9):1-6.(CUI Z B, LI Y, MAO T, et al. Scratch detection of plastics based on preprocessing and convolutional neural network[J]. Die and Mould Industry, 2017,43(9):1-6.)
[4] 李克斌,余厚云,周申江.基于形态学特征的机械零件表面划痕检测[J].光学学报,2018,38(8):815027-1-815027-7.(LI K B, YU H Y, ZHOU S J. Scratch detection for the surface of mechanical parts based on morphological features[J]. Acta Optica Sinica, 2018,38(8):815027-1-815027-7.)
[5] 汤勃,孔建益,伍世虔.机器视觉表面缺陷检测综述[J].中国图象图形学报,2017,22(12):1640-1663.(TANG B, KONG J Y, WU S Q. Review of surface defect detection based on machine vision[J]. Journal of Image and Graphics, 2017,22(12):1640-1663.)
[6] 胡文瑾,李战明,刘仲民.一种基于小波分析的唐卡图像划痕检测[J].光学技术,2012,38(6):751-755.(HU W J, LI Z M, LIU Z M. Scratch detection algorithm based on wavelet analysis for Thangka image[J]. Optical Technique, 2012,38(6):751-755.)
[7] 周鹏,徐科,刘顺华.基于剪切波和小波特征融合的金属表面缺陷识别方法[J].机械工程学报,2015,51(6):98-103.(ZHOU P, XU K, LIU S H. Surface defect recognition for metals based on feature fusion of shearlets and wavelets[J]. Journal of Mechanical Engineering, 2015,51(6):98-103.)
[8] 马云鹏,李庆武,何飞佳,等.金属表面缺陷自适应分割算法[J].仪器仪表学报,2017,38(1):245-251.(MA Y P, LI Q W, HE F J, et al. Adaptive segmentation algorithm for metal surface defects[J]. Chinese Journal of Scientific Instrument, 2017,38(1):245-251.)
[9] 郭皓然,邵伟,周阿维,等.全局阈值自适应的高亮金属表面缺陷识别新方法[J].仪器仪表学报,2017,38(11):2797-2804.(GUO H R, SHAO W, ZHOU A W, et al. Novel defect recognition method based on adaptive global threshold for highlight metal surface[J]. Chinese Journal of Scientific Instrument, 2017,38(11):2797-2804.)
[10] JOHNSON J, ALAHI A, LI F F. Perceptual losses for real-time style transfer and super-resolution[C]//Proceedings of the 2016 European Conference on Computer Vision. Berlin:Springer, 2016:694-711.
[11] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088):533-536.
[12] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:770-778.
[13] BOTTOU, CURTIS F E, NOCEDA J, et al. Optimization methods for large-scale machine learning[J]. SIAM Review, 2016, 60(2):223-311.
[14] RADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. ArXiv Preprint, 2016, 2016:1511.06434.
[15] LIM B, LEE K M. Deep recurrent ResNet for video super-resolution[C]//Proceedings of the 2018 IEEE Conference on Asia-pacific Signal and Information Processing Association Summit. Washington, DC:IEEE Conputer Society, 2018:643-648.
[16] IOFFE S, SZEGEDY C. Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:448-456.
[17] NAIR V, HINTON G E. Rectified linear units improve restricted boltzmann machines[C]//Proceedings of the 2010 International Conference on Machine Learning. New York:ACM, 2010:807-814.
[18] SIMONVAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//Proceedings of the 2015 International Conference on Learning. Washington, DC:IEEE Computer Society, 2015:687-699.
[19] YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions[C]//Proceedings of the 2016 International Conference on Learning. Washington, DC:IEEE Computer Society, 2016:511-524.
[20] KINGMA D, BA J. Adam:a method for stochastic optimization[C]//Proceedings of the 2014 International Conference on Learning. Washington, DC:IEEE Computer Society, 2014:248-263.
[21] HOWARD A G, ZHU M, CHEN B, et al. MobileNets:efficient convolutional neural networks for mobile vision applications[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2017:1056-1065.
[22] ZHANG X, ZHOU X, LIN M, et al. ShuffleNet:an extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2017:563-572.

Surface scratch recognition method based on deep neural network

基于深度神经网络的表面划痕识别方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	WANG Hebing, ZHANG Chunmei. Facial landmark detection based on ResNeXt with asymmetric convolution and squeeze excitation [J]. Journal of Computer Applications, 2021, 41(9): 2741-2747.
[2]	SONG Zhongshan, LIANG Jiarui, ZHENG Lu, LIU Zhenyu, TIE Jun. Remote sensing scene classification based on bidirectional gated scale feature fusion [J]. Journal of Computer Applications, 2021, 41(9): 2726-2735.
[3]	LI Kangkang, ZHANG Jing. Multi-layer encoding and decoding model for image captioning based on attention mechanism [J]. Journal of Computer Applications, 2021, 41(9): 2504-2509.
[4]	ZHANG Yongbin, CHANG Wenxin, SUN Lianshan, ZHANG Hang. Detection method of domains generated by dictionary-based domain generation algorithm [J]. Journal of Computer Applications, 2021, 41(9): 2609-2614.
[5]	ZHAO Hong, KONG Dongyi. Chinese description of image content based on fusion of image feature attention and adaptive attention [J]. Journal of Computer Applications, 2021, 41(9): 2496-2503.
[6]	XU Jianglang, LI Linyan, WAN Xinjun, HU Fuyuan. Indoor scene recognition method combined with object detection [J]. Journal of Computer Applications, 2021, 41(9): 2720-2725.
[7]	CAO Yuhong, XU Hai, LIU Sun'ao, WANG Zixiao, LI Hongliang. Review of deep learning-based medical image segmentation [J]. Journal of Computer Applications, 2021, 41(8): 2273-2287.
[8]	QIN Binbin, PENG Liangkang, LU Xiangming, QIAN Jiangbo. Research progress on driver distracted driving detection [J]. Journal of Computer Applications, 2021, 41(8): 2330-2337.
[9]	HUANG Chengcheng, DONG Xiaoxiao, LI Zhao. Deep pipeline 5×5 convolution method based on two-dimensional Winograd algorithm [J]. Journal of Computer Applications, 2021, 41(8): 2258-2264.
[10]	ZENG Xiangyin, ZHENG Bochuan, LIU Dan. Detection of left and right railway tracks based on deep convolutional neural network and clustering [J]. Journal of Computer Applications, 2021, 41(8): 2324-2329.
[11]	WU Guangli, LI Leiting, GUO Zhenzhou, WANG Chengxiang. Video summarization generation model based on improved bi-directional long short-term memory network [J]. Journal of Computer Applications, 2021, 41(7): 1908-1914.
[12]	TAN Daoqiang, ZENG Cheng, QIAO Jinxia, ZHANG Jun. Shadow detection method based on hybrid attention model [J]. Journal of Computer Applications, 2021, 41(7): 2076-2081.
[13]	YANG Su, OUYANG Zhi, DU Nisuo. Unsupervised parallel hash image retrieval based on correlation distance [J]. Journal of Computer Applications, 2021, 41(7): 1902-1907.
[14]	GAO Qinquan, HUANG Bingcheng, LIU Wenzhe, TONG Tong. Bamboo strip surface defect detection method based on improved CenterNet [J]. Journal of Computer Applications, 2021, 41(7): 1933-1938.
[15]	ZHANG Hui, ZHANG Nana, HUANG Jun. Multi-angle head pose estimation method based on optimized LeNet-5 network [J]. Journal of Computer Applications, 2021, 41(6): 1667-1672.