计算机科学 ›› 2022, Vol. 49 ›› Issue (11A): 211100090-6.doi: 10.11896/jsjkx.211100090
郭文龙, 刘芳华, 吴万毅, 李冲, 肖鹏, 刘朝
GUO Wen-long, LIU Fang-hua, WU Wan-yi, LI Chong, XIAO Peng, LIU Chao
摘要： 由于需要通过木板表面缺陷对木板分级,而人工检测存在一定问题。为解决木板表面缺陷识别问题,提出一种融合ViT的卷积神经网络模型,用于提高缺陷识别的准确率。为此,收集裂缝、虫眼、节子和纹理4种木板表面缺陷图片,其中裂缝和虫眼图片数量远少于节子和纹理。为解决模型训练时样本不均衡问题,利用ProGAN对裂缝和虫眼图片进行训练并生成同类型缺陷图片,以增加其数量,使4种图片数量保持平衡,并在实验前对缺陷图片进行数据增强并添加椒盐噪声,整理得到所需图片数据集。基于融合ViT的卷积神经网络模型,利用数据集验证两种不同激活函数的模型,结果表明使用GELU作为激活函数的模型性能更高。并测试不同的transformer深度时模型的性能,得到的模型缺陷识别的最高准确率可达到98.54%。实验结果表明,融合ViT的卷积神经网络模型是可行的,为木板表面缺陷自动检测提供了新思路。
中图分类号:
| [1]LI H,WU J N,YUAN W Q,et al.Research on real-time wood classification method based on visual significance [J].Journal of Instrumentation,2018,39(12):237-244. [2]RAHIDDIN R N N,HASHIM U R,ISMAIL N H,et al.Classification of wood defect images using local binary pattern variants[J].International Journal of Advances in Intelligent Informa-tics,2020,6(1):36-45. [3]CAVALIN P,OLIVEIRA L S,KOERICH A L,et al.Wood defect detection using grayscale images and an optimized feature set[C]//IECON 2006-32nd Annual Conference on IEEE Industrial Electronics.IEEE,2006:3408-3412. [4]RUZ G A,ESTEVEZ P A,PEREZ C A.A neurofuzzy color image segmentation method for wood surface defect detection[J].Forest Products Journal,2005,55(4):52-58. [5]HU J F,ZHAO Y F,CAO J.wood surface defect image segmentation algorithm based on super-pixel [J].Journal of Northeast Forestry University,2015,43(10):97-102 [6]LI S L,YUAN W Q,YANG J Y,et al.Wood defect classification based on local binary difference incentive model [J].Journal of Instrumentation,2019,40(6):68-77. [7]KARRAS T,AILA T,LAINE S,et al.Progressive growing of gans for improved quality,stability,and variation[J].arXiv:1710.10196,2017. [8]HENDRYCKS D,GIMPEL K.Gaussian error linear units(gelus)[J].arXiv:1606.08415,2016. [9]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[C]//International Conference on Learning Representations.2015. [10]DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.An ima-ge is worth 16x16 words:Transformers for image recognition at scale[J].arXiv:2010.11929,2020. [11]HAN B,ZENG S W.Plant leaf recognition based on multi feature fusion and convolution neural network [J].Computer Science,2021,48(S1):113-117 [12]XU Y G,ZHONG M,WU Z Z,et al.Texture cloth defect detection method based on deep learning [J/OL].Automation Report:1-16.[2021-11-05].https://doi.org/10.16383/j.aas.c200148. [13]LIU X T,WANG W,LI Z Y,et al.Recognition algorithm of red and white blood cells in urine based on Improved BP neural network [J].Computer Science,2020,47(2):102-105. [14]DING F,ZHUANG Z,LIU Y,et al.Detecting defects on solid wood panels based on an improved SSD algorithm[J].Sensors,2020,20(18):5315. [15]GAO M,CHEN J,MU H,et al.A Transfer Residual Neural Network Based on ResNet-34 for Detection of Wood Knot Defects[J].Forests,2021,12(2):212. [16]PAN S,FAN S,WONG S W K,et al.Ellipse detection and loca-lization with applications to knots in sawn lumber images[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.2021:3892-3901. [17]CHEN H,WANG Y,GUO T,et al.Pre-trained image processing transformer[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:12299-12310. [18]HUANG Y,QIU C,WANG X,et al.A compact convolutional neural network for surface defect inspection[J].Sensors,2020,20(7):1974. [19]JABO S.Machine vision for wood defect detection and classification[D].Gothenburg,Sweden:Department of Signal and Systems Chalmers University of Technology,2011. [20]KHAN S,NASEER M,HAYAT M,et al.Transformers in vision:A survey[J].arXiv:2101.01169,2021. |
| [1] | 周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026 |
| [2] | 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204 |
| [3] | 饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277 |
| [4] | 汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108 |
| [5] | 陈泳全, 姜瑛. 基于卷积神经网络的APP用户行为分析方法 Analysis Method of APP User Behavior Based on Convolutional Neural Network 计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121 |
| [6] | 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153 |
| [7] | 孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061 |
| [8] | 檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064 |
| [9] | 李宗民, 张玉鹏, 刘玉杰, 李华. 基于可变形图卷积的点云表征学习 Deformable Graph Convolutional Networks Based Point Cloud Representation Learning 计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023 |
| [10] | 王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099 |
| [11] | 郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077 |
| [12] | 姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046 |
| [13] | 胡艳羽, 赵龙, 董祥军. 一种用于癌症分类的两阶段深度特征选择提取算法 Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification 计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092 |
| [14] | 张颖涛, 张杰, 张睿, 张文强. 全局信息引导的真实图像风格迁移 Photorealistic Style Transfer Guided by Global Information 计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036 |
| [15] | 戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮. 基于DNGAN的磁共振图像超分辨率重建算法 Super-resolution Reconstruction of MRI Based on DNGAN 计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105 |
|
||
首页