纺织学报 ›› 2022, Vol. 43 ›› Issue (08): 67-73.doi: 10.13475/j.fzxb.20210505007

• 纺织工程 • 上一篇    下一篇

结合图像频域和空间域的纬编针织物密度检测方法

邓中民, 胡灏东, 于东洋, 王文, 柯薇()   

  1. 武汉纺织大学 省部共建纺织新材料与先进加工技术国家重点实验室, 湖北 武汉 430200
  • 收稿日期:2021-05-20 修回日期:2022-04-15 出版日期:2022-08-15 发布日期:2022-08-24
  • 通讯作者: 柯薇
  • 作者简介:邓中民(1963—),男,教授,博士。主要研究方向为数字化纺织。

Density detection method of weft knitted fabrics making use of combined image frequency domain and spatial domain

DENG Zhongmin, HU Haodong, YU Dongyang, WANG Wen, KE Wei()   

  1. State Key Laboratory of New Textile Materials and Advanced Processing Technology, Wuhan Textile University, Wuhan, Hubei 430200, China
  • Received:2021-05-20 Revised:2022-04-15 Published:2022-08-15 Online:2022-08-24
  • Contact: KE Wei

摘要:

为解决当前基于图像处理测量纬编针织物密度准确度不高、稳定性较差等问题,提出一种结合频域和空间域来测定针织物密度的方法。首先通过离散小波变换重构针织物线圈图像获得线圈结构清晰的图像,再分别提取线圈灰度及二值图的灰度曲线。利用提出的基于概率密度统计的波谷坐标校验算法,结合线圈坐标校验算法获得实际线圈所在列坐标;再利用八邻域广度优先搜索算法求出纬编针织物横、纵方向的线圈个数,得到针织物横密和纵密。结果表明,密度检测方法与人工测量数据相比误差小于1.7%,该方法适用性好,运算量小,准确率高,可实现纬编针织物密度的自动化测量。

关键词: 针织物密度, 图像处理, 灰度曲线, 连通域, 密度检测方法

Abstract:

Aiming at the problems of low accuracy and poor applicability in measuring the density of weft knitted fabrics based on image processing, this paper presents a method for locating the loop position based on the gray curve of weft knitted fabric image to measure the fabric density, which highlights the loop image based on discrete wavelet transform. By extracting the gray curves of weft knitted fabrics and binary image respectively, the coordinates of the actual loop column were obtained by using the trough coordinate verification algorithm based on probability density statistics and the loop coordinate verification algorithm proposed in this study. The eight-neighborhood search algorithm was used to calculate the number of loops in the transverse and longitudinal directions of the weft knitted fabric, and the course and wale densities of the weft knitted fabric were obtained. Compared with the existing methods based on image processing, the method proposed in this paper involves less computation, and the error is less than 1.7% compared with the standard data, which shows that this method has fast measurement and high accuracy, and it is beneficial for automatic measurement of weft knitted fabric density.

Key words: density of knitted fabric, image processing, gray curve, connected domain, density detection method

中图分类号: 

  • TS107

图1

织物结构示意图"

图2

总体流程图"

图3

图像倾斜矫正"

图4

离散小波分解图"

图5

图像灰度曲线"

图6

二值化处理对比图"

图7

纱线间隔区域与线圈区域断开示意图"

图8

消去圈柱间隙列前后图像"

图9

形态学运算前后的图像"

图10

二值图像灰度曲线"

表1

部分实验测量结果及对比"

试样
编号
本文方法 横密误
差/%
纵密误
差/%
人工检测 方法1 方法2
横密 纵密 时间/s 横密 纵密 时间/s 横密 纵密 时间/s 横密 纵密 时间/s
1 90.5 137.1 0.44 0.56 0.07 90.0 137.0 90.0 136.8 0.46 181.1 138.1 1.30
2 61.0 74.6 0.37 1.67 0.50 60.0 75.0 60.0 74.8 0.51 60.7 75.0 0.46
3 59.8 84.0 0.23 0.33 1.18 60.0 85.0 59.5 85.2 0.41 60.0 84.4 0.32
4 29.8 60.9 0.21 0.67 1.50 30.0 60.0 30.0 59.2 0.43 28.2 59.4 0.34
5 49.7 75.3 0.81 0.60 0.40 50.0 75.0 20.0 565.8 3.24 48.2 74.8 0.37
6 75.5 108.9 0.65 0.67 1.00 75.0 110.0 74.1 109.2 0.68 74.7 112.7 0.61

图11

方法1处理流程图"

[1] 潘如如, 高卫东, 李忠健, 等. 基于傅里叶图像分析的机织物密度检测[J]. 中国科技论文, 2015(20):2416-2421.
PAN Ruru, GAO Weidong, LI Zhongjian, et al. Woven fabric density inspection using fourier image analysis[J]. China Sciencepaper, 2015(20):2416-2421.
[2] 马云芳, 王小华. 功率谱分析在机织物组织纹理识别中的应用[J]. 毛纺科技, 2007, 35(4):56-60.
MA Yunfang, WANG Xiaohua. Fabric texture feature extraction based on power spectrum[J]. Wool Textile Journal, 2007, 35(4):56-60.
[3] 彭然, 胡立文, 邓中民. 基于Radon变换和能量曲线的机织物密度检测[J]. 棉纺织技术, 2021, 49(4):16-20.
PENG Ran, HU Liwen, DENG Zhongmin. Detection of woven fabric density based on Radon transform and energy curve[J]. Cotton Textile Technology, 2021, 49(4):16-20.
[4] 丁雪荣, 宋广礼. 应用MATLAB图像处理技术测量纬编针织物密度的研究[J]. 针织工业, 2006(1):60-62.
DING Xuerong, SONG Guangli. A research on the density measurement of weft-knitted fabric using the image manipulating technology of MatLab[J]. Knitting Industries, 2006(1):60-62.
[5] 王庆涛, 马崇启, 高雨田, 等. 基于频域特征点提取的素色机织物密度识别算法[J]. 纺织学报, 2014, 35(4):47-51.
WANG Qingtao, MA Chongqi, GAO Yutian, et al. Identification algorithm of plain woven fabric density via feature point extraction in frequency domain[J]. Journal of Textile Research, 2014, 35(4):47-51.
[6] 赵延旭, 龙海如. 利用图像处理技术自动测量针织物密度的研究[J]. 东华大学学报(自然科学版), 2004, 30(6):46-49.
ZHAO Yanxu, LONG Hairu. Study on the automatic measurement of the density of knitted fabrics by image progressing[J]. Journal of Donghua University (Natural Science), 2004, 30(6):46-49.
[7] 孟朔, 夏旭文, 潘如如, 等. 基于卷积神经网络的机织物密度均匀性检测[J]. 纺织学报, 2021, 42(2):101-106.
MENG Shuo, XIA Xuwen, PAN Ruru, et al. Detection of fabric density uniformity based on convolutional neural network[J]. Journal of Textile Research, 2021, 42(2):101-106.
[8] 张孝超, 李平, 金福江. 应用图像空域法的针织物密度在线测量[J]. 纺织学报, 2015, 36(11):138-145.
ZHANG Xiaochao, LI Ping, JIN Fujiang. Online measurement for density of knitted fabric by spatial domain image method[J]. Journal of Textile Research, 2015, 36(11):138-145.
[9] MUKHOPADHYAY P, CHAUDHURI B B. A survey of Hough transform[J]. Pattern Recognition, 2015, 48(3):993-1010.
doi: 10.1016/j.patcog.2014.08.027
[10] YANOWITZ S D, BRUCKSTEIN A M. A new method for image segmentation[J]. Computer Vision, Graphics, and Image Processing, 1989, 46(1):82-95.
doi: 10.1016/S0734-189X(89)80017-9
[11] GALLUCCIO L, MICHEL O, COMON P, et al. Graph based K-means clustering[J]. Signal Processing, 2012, 92(9):1970-1984.
doi: 10.1016/j.sigpro.2011.12.009
[1] 马运娇, 王蕾, 潘如如, 高卫东. 基于平面镜成像的纱线条干三维合成校准方法[J]. 纺织学报, 2022, 43(07): 55-59.
[2] 周其洪, 彭轶, 岑均豪, 周申华, 李姝佳. 基于机器视觉的细纱接头机器人纱线断头定位方法[J]. 纺织学报, 2022, 43(05): 163-169.
[3] 张荣根, 冯培, 刘大双, 张俊平, 杨崇倡. 涤纶工业长丝毛丝在线检测系统的研究[J]. 纺织学报, 2022, 43(04): 153-159.
[4] 熊晶晶, 杨雪, 苏静, 王鸿博. 基于图像技术的织物导湿性能测试方法[J]. 纺织学报, 2021, 42(12): 70-75.
[5] 吕文涛, 林琪琪, 钟佳莹, 王成群, 徐伟强. 面向织物疵点检测的图像处理技术研究进展[J]. 纺织学报, 2021, 42(11): 197-206.
[6] 夏旭文, 孟朔, 潘如如, 高卫东. 基于改进帧间差分法的经纱撞筘拥纱在线检测[J]. 纺织学报, 2021, 42(06): 91-96.
[7] 江燕婷, 严庆帅, 辛斌杰, 高琮, 施楣梧. 纺织品单向导水性能测试方法分析[J]. 纺织学报, 2021, 42(05): 51-58.
[8] 李东洁, 郭帅, 杨柳. 基于改进图像阈值分割算法的纱线疵点检测[J]. 纺织学报, 2021, 42(03): 82-88.
[9] 唐千惠, 王蕾, 高卫东. 基于图像处理的织物保形性检测[J]. 纺织学报, 2021, 42(03): 89-94.
[10] 孟朔, 夏旭文, 潘如如, 周建, 王蕾, 高卫东. 基于卷积神经网络的机织物密度均匀性检测[J]. 纺织学报, 2021, 42(02): 101-106.
[11] 张铮烨, 辛斌杰, 邓娜, 陈阳, 邢文宇. 基于边界跟踪测量麻纤维横截面参数的算法研究与应用[J]. 纺织学报, 2020, 41(02): 39-43.
[12] 吴义伦, 李忠健, 潘如如, 高卫东, 张宁. 应用色纺纱图像的纬编针织物外观模拟[J]. 纺织学报, 2019, 40(06): 111-116.
[13] 黄嘉俊, 柯薇, 王静, 邓中民. 基于计算机视觉的牛仔服装色差检测评级系统[J]. 纺织学报, 2019, 40(05): 163-169.
[14] 王文帝, 辛斌杰, 邓娜, 李佳平, 刘宁娟. 单一视角下自适应阈值法的纱线毛羽识别及其应用[J]. 纺织学报, 2019, 40(05): 150-156.
[15] 蔡逸超, 周晓, 宋明峰, 牟新刚. 应用多尺度多方向模板卷积的筒子纱缺陷检测[J]. 纺织学报, 2019, 40(04): 152-157.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!