方向性纹理织物疵点检测方法研究

管声启

GUAN Shengqi

（School of Mechanical and Electronic Engineering,Xi’an Polytechnic University,Xi’an 710048,China）

Received:2010-04-12 Revised:2010-08-15 Online:2011-03-25 Published:2011-05-01

摘要：

通过分析方向性织物纹理的特点，提出了一种织物疵点检测新的方法。首先根据正常纹理Hough变换

确定织物纹理的纹路方向；然后采用方向性小波对织物纹理图像进行方向性的分解，并在此基础上从分解后

的各细节子图中提取子窗口的特征；最后通过BP神经网络进行织物疵点识别。实验结果表明了该方法的有效

性。

关键词: 方向性纹理, Hough变换, 小波分解, 疵点检测

Abstract:

By analyzing the characteristics of directional fabric textures, a new method for

defect detection is presented. Firstly, the main lines of texture fabric texture are detected

by the normal fabric texture Hough transform. Then, fabric texture images are decomposed by

the directional wavelet. On this basis, the subwindows of characteristics are extracted from

the detailed subimages. Finally, the fabric defects are identified by the BP neural network.

The experimental results show that this method is effective.

Key words: directional texture;Hough transform;wavelet decomposition;defect detection

管声启. 方向性纹理织物疵点检测方法研究[J]. J4, 2011, 33(3): 73-76.

GUAN Shengqi. A Detection Method of Directional Texture Fabric Defects[J]. J4, 2011, 33(3): 73-76.

[1]	孔锐1,2,揭英达1,程霖1. 基于扫描线处理的指针式仪表快速读数算法[J]. 计算机工程与科学, 2017, 39(07): 1309-1316.
[2]	廖宇，郭黎. 一种运动模糊图像的模糊参数估计方法[J]. J4, 2014, 36(10): 2002-2008.
[3]	方建军1，杜明芳1,2 ，庞睿1. 基于小波分析和概率Hough变换的书脊视觉识别[J]. J4, 2014, 36(01): 126-131.
[4]	张冀1,2，王俊宏1，尉迟明1，丁明跃1，侯文广1. 基于计算机视觉的汽车仪表指针检测方法[J]. J4, 2013, 35(3): 134-139.
[5]	邹北骥,胡艺龄,辛国江. 基于小波分解和PCNN的图像融合方法[J]. J4, 2011, 33(2): 102-107.
[6]	吴禹昊，陈天泽，粟毅. 基于方向ROEWA算子的高分辨率SAR图像道路提取[J]. J4, 2010, 32(8): 71-74.
[7]	陈苏1，林嘉宇2. 基于Hough变换的实验数据坏点剔除方法[J]. J4, 2010, 32(8): 67-70.
[8]	秦筱楲[1] 丁明跃[2]. 基于图像分析的后视镜失真率自动检测方法[J]. J4, 2005, 27(7): 57-59.
[9]	黄本雄段善维胡海. 图像小波分解的FPGA实现[J]. J4, 2005, 27(3): 32-34.
[10]	黄晓雯赵杰唐贤瑛. 基于小波分解的嵌入式水印[J]. J4, 2004, 26(8): 48-49.
[11]	付瑶刘志镜等. 基于小波分析的人脸特征提取方法[J]. J4, 2002, 24(6): 52-54.

PDF