改进频率调谐显著算法在疵点辨识中的应用

doi:10.13475/j.fzxb.20170402007

摘要/Abstract

摘要：

为提高疵点检测效率和准确率，提出用改进频率调谐显著（FT）算法替代 Gabor 小波方法预处理疵点图像，强化疵点特征向量灵敏度。分析了FT 算法中高斯滤波器模板、Lab 颜色空间、高斯滤波图像中椒盐噪声和 HSV 颜色空间不同通道取值范围不一致对疵点识别的影响，并提出了相应改进方法。利用改进 FT 算法进行图像显著处理；使用灰度共生矩阵方法对疵点显著图进行特征提取；利用概率神经网络分类器分类，检测是否存在疵点。对 2 种不同纹理面料的检测结果表明：改进 FT 算法较改进前计算时间增加约8%，但疵点检测准确率提高18% ～25%；与 Gabor 小波相比，检测准确率基本持平，但计算时间缩短约70%。

关键词: 疵点检测, 显著图, 频域协调, 图像处理

Abstract:

In order to improve the efficiency and accuracy of fabric defect detection, a novel defect detection algorithm with improved frequency-tuned salient region (FT) to replace the Gabor wavelet method was proposed to improve the contrast ratio of fabric defection image and enbance the sensitivity of feature vectors. The influence factors of FT algorithm on the recognition precision of fabric defect including Gauss filter template, Lab color space, the salt and pepper noise in the image of the filter and the different ranges of HSV color space were analyzed. The FT algorithm was improved based on the analytic result. The fabric images were highlighted by the improved FT algorithm. Simultaneously, the gray-level co-occurrence matrix method was to extract the feature vector from the highlighted image. Finally, probabilistic neural network was employed to detect the defect on the fabric image. Through the detection of 2 kinds of fabrics with different textures, the experimental results show that the computational time of the improved FT algorithm is prolonged by about 8%. Meanwhile, the accuracy of defect detection increases by 18%~25%. Compared with the Gabormethod, the detection accuracy is substanially the same, but the computation time is shortened by about 70%.

Key words: defect detection, salient map, frequency-tuned, image processing

王传桐胡峰徐启永吴雨川余联庆. 改进频率调谐显著算法在疵点辨识中的应用[J]. 纺织学报, 2018, 39(03): 154-160.

参考文献

[1] 管声启, 石秀华. 基于频域滤波的织物疵点检测[J].计算机应用, 2008, 28(10):2673-2675. GUAN Shengqi，SHI Xiuhua. Fabric defects detection based on frequency domain filtering[J]. Journal of Computer Application, 2008, 28(10):2673-2675. [2] 屈博, 卢朝阳, 李静, 等. 一种改进的多通道Gabor滤波器布匹瑕疵检测方法[J].纺织学报, 2009, 30(12):37-40. QU Bo, LU Zhaoyang, LI Jing, et al. An improved multichannel Gabor filter algorithm for fabric defect detection[J]. Journal of Textile Research, 2009, 30(12):37-40. [3] 王传桐, 胡峰, 徐启永, 等. 基于Gabor滤波簇和等距映射算法的疵点检测方法[J]. 纺织学报 WANG Chuantong, HU Feng, XU Qiyong, et al. Detection of fabric defects based on Gabor filters and Isomap[J]. Journal of Textile Research, [4] 林如意. 基于图像处理技术的纺织品瑕疵检测方法[D]. 杭州：杭州电子科技大学，2013：11-14 LIN Ruyi. Fabric Defect Detection Based on Image Processing Technology[D]. Hangzhou: Hangzhou Dianzi UniVersiy, 2013：11-14 [5] RADHAKISHNA Achanta, SHEILA Hemami, FRANCISCO Estrada, et al. Frequency-tuned Salient Region Detection [C]. IEEE Conference on Computer Vision & Pattern Recognition, 2009,?22(9-10):1597-1604 [6] 于乃昭，姚志均，杨波. 一种改进的频率调谐显著性检测方法[J]. 《舰船电子对抗》,?2013,?36(1):57-61 YU Naizhao, YAO Zhijun, YANG Bo. An Improved Frequency Tuned-based Saliency Detection Method [J]. Shipboard Electronic Countermeasure, 2013 ,?36(1):57-61 [7] 刘洲峰, 赵全军, 李春雷, 等. 基于局部统计与整体显著性的织物疵点检测算法[J]. 纺织学报, 2014,35(11):62-67. LIU Fengzhou, ZHAO Quanjun, LI Chunlei, et al. Fabric defect detection algorithm using local statistic features and global saliency analysis[J]. Journal of Textile Research, 2014,35(11):62-67. [8] LIU Yan, GU Xueping. Skeleton-network reconfiguration based on topological characteristics of scale-free networks and discrete particle swarm optimization [J]. IEEE Transactions on Power Systems, 2007, 22(3):1267-1274. [9] ALBERTO García-Villoria, RAFAEL Pastor. Introducing dynamic diversity into a discrete particle swarm optimization [J]. Computer and Operation Research, 2009, 36(3):951-966. [10] 胡峰, 苏讯, 刘伟, 等. 基于改进局部线性嵌入算法的故障特征提取方法[J]. 振动与冲击，2015, 34(15):201-204. HU Feng, SU Xun, LIU Wei, et al. Fault Feature Extraction Based on Improved Locally Linear Embedding [J]. Journal of Vibration and Shock, 2015, 34(15):201-204. [11] 胡峰, 王传桐, 吴雨川, 等. 基于改进监督LLE算法的故障特征提取方法[J]. 振动与冲击，2015(21):119-123. HU Feng, WANG Chuantong, WU Yuchuan, et al. Fault features extraction based on improved supervised locally linear embedding [J] Journal of Vibration and Shock, 2015(21):119-123., [1] 管声启, 石秀华. 基于频域滤波的织物疵点检测[J].计算机应用, 2008, 28(10):2673-2675. GUAN Shengqi，SHI Xiuhua. Fabric defects detection based on frequency domain filtering[J]. Journal of Computer Application, 2008, 28(10):2673-2675. [2] 屈博, 卢朝阳, 李静, 等. 一种改进的多通道Gabor滤波器布匹瑕疵检测方法[J].纺织学报, 2009, 30(12):37-40. QU Bo, LU Zhaoyang, LI Jing, et al. An improved multichannel Gabor filter algorithm for fabric defect detection[J]. Journal of Textile Research, 2009, 30(12):37-40. [3] 王传桐, 胡峰, 徐启永, 等. 基于Gabor滤波簇和等距映射算法的疵点检测方法[J]. 纺织学报 WANG Chuantong, HU Feng, XU Qiyong, et al. Detection of fabric defects based on Gabor filters and Isomap[J]. Journal of Textile Research, [4] 林如意. 基于图像处理技术的纺织品瑕疵检测方法[D]. 杭州：杭州电子科技大学，2013：11-14 LIN Ruyi. Fabric Defect Detection Based on Image Processing Technology[D]. Hangzhou: Hangzhou Dianzi UniVersiy, 2013：11-14 [5] RADHAKISHNA Achanta, SHEILA Hemami, FRANCISCO Estrada, et al. Frequency-tuned Salient Region Detection [C]. IEEE Conference on Computer Vision & Pattern Recognition, 2009,?22(9-10):1597-1604 [6] 于乃昭，姚志均，杨波. 一种改进的频率调谐显著性检测方法[J]. 《舰船电子对抗》,?2013,?36(1):57-61 YU Naizhao, YAO Zhijun, YANG Bo. An Improved Frequency Tuned-based Saliency Detection Method [J]. Shipboard Electronic Countermeasure, 2013 ,?36(1):57-61 [7] 刘洲峰, 赵全军, 李春雷, 等. 基于局部统计与整体显著性的织物疵点检测算法[J]. 纺织学报, 2014,35(11):62-67. LIU Fengzhou, ZHAO Quanjun, LI Chunlei, et al. Fabric defect detection algorithm using local statistic features and global saliency analysis[J]. Journal of Textile Research, 2014,35(11):62-67. [8] LIU Yan, GU Xueping. Skeleton-network reconfiguration based on topological characteristics of scale-free networks and discrete particle swarm optimization [J]. IEEE Transactions on Power Systems, 2007, 22(3):1267-1274. [9] ALBERTO García-Villoria, RAFAEL Pastor. Introducing dynamic diversity into a discrete particle swarm optimization [J]. Computer and Operation Research, 2009, 36(3):951-966. [10] 胡峰, 苏讯, 刘伟, 等. 基于改进局部线性嵌入算法的故障特征提取方法[J]. 振动与冲击，2015, 34(15):201-204. HU Feng, SU Xun, LIU Wei, et al. Fault Feature Extraction Based on Improved Locally Linear Embedding [J]. Journal of Vibration and Shock, 2015, 34(15):201-204. [11] 胡峰, 王传桐, 吴雨川, 等. 基于改进监督LLE算法的故障特征提取方法[J]. 振动与冲击，2015(21):119-123. HU Feng, WANG Chuantong, WU Yuchuan, et al. Fault features extraction based on improved supervised locally linear embedding [J] Journal of Vibration and Shock, 2015(21):119-123.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

[1]	陆奕辰王蕾唐千惠潘如如高卫东. 应用图像处理的纱线黑板毛羽量检测与评价[J]. 纺织学报, 2018, 39(08): 144-149.
[2]	王雯雯高畅刘基宏. 应用卷积神经网络的细纱断纱锭位识别[J]. 纺织学报, 2018, 39(06): 136-141.
[3]	何晓昀韦平张林邓斌攸潘云峰苏真伟. 基于深度学习的籽棉中异性纤维检测方法[J]. 纺织学报, 2018, 39(06): 131-135.
[4]	王雯雯刘基宏. 应用优化霍夫变换的细纱断头检测[J]. 纺织学报, 2018, 39(04): 36-41.
[5]	牟新刚蔡逸超周晓陈国良. 基于机器视觉的筒子纱缺陷在线检测系统[J]. 纺织学报, 2018, 39(01): 139-145.
[6]	何峰周亚同赵翔宇刘猛张忠伟. 纹理织物疵点窗口跳步形态学法检测[J]. 纺织学报, 2017, 38(10): 124-131.
[7]	王晓予向军潘如如梁惠娥高卫东. 服饰刺绣图案的自动提取与色块分割[J]. 纺织学报, 2017, 38(09): 120-126.
[8]	路凯钟跃崎朱俊平柴新玉. 基于视觉词袋模型的羊绒与羊毛快速鉴别方法[J]. 纺织学报, 2017, 38(07): 130-134.
[9]	张继东薛元张杰郭明瑞魏晓婷高卫东 . 应用混色纱纹理信息的纬编针织物模拟[J]. 纺织学报, 2017, 38(07): 148-154.
[10]	张宁李忠健潘如如高卫东韩要宾. 采用色纺纱图像的真实感色织物模拟[J]. 纺织学报, 2017, 38(05): 37-42.
[11]	韦平张林刘翔王冬苏真伟. 籽棉中异性纤维的双光源成像检测方法[J]. 纺织学报, 2017, 38(04): 32-38.
[12]	刘成霞韩永华. 模拟实际着装的织物抗皱性测试方法[J]. 纺织学报, 2017, 38(03): 56-60.
[13]	王传桐胡峰徐启永吴雨川余联庆. 采用Gabor滤波簇和等距映射算法的织物疵点检测方法[J]. 纺织学报, 2017, 38(03): 162-167.
[14]	李春雷高广帅刘洲峰刘秋丽李文羽. 应用方向梯度直方图和低秩分解的织物疵点检测算法[J]. 纺织学报, 2017, 38(03): 149-154.
[15]	李冠志赵强汪军 Gong Hugh . 纱线截面压缩变形仿真与验证[J]. 纺织学报, 2017, 38(02): 184-190.