噪声干扰下的防羽布疵点检测算法  

Defect detection algorithm of down-proof fabric under noise interference

作　　者：张团善[1] 石玮 ZHANG Tuanshan;SHI Wei(School of Mechanical and Electrical Engineering,Xi’an Polytechnic University,Xi’an 710048,China)

机构地区：[1]西安工程大学机电工程学院,陕西西安710048

出　　处：《西安工程大学学报》2020年第1期14-19,共6页Journal of Xi’an Polytechnic University

基　　金：国家自然科学基金(61701384)。

摘　　要：针对在光照不均、布匹不平整、疵点特征不明显等噪声干扰条件下,防羽布的疵点检测困难、检测精度低等问题,提出一种抗干扰条件的防羽布疵点检测算法。首先将RGB图像转换为灰度图像,然后构建基矩阵并计算其区域均值;计算得到区域差异矩阵,并将差异矩阵内元素与定义的疵点因子进行比较,得到二值图像;最后经过中值滤波消除噪声干扰。通过3048个样本实验,发现对防羽布疵点检测精度达到92.7%以上,误检率在6.9%以下。该算法适用于非色差类疵点检测,能够实现在噪声干扰情况下准确分割防羽布表面疵点,具有更好的抗噪能力,对防羽布疵点检测有实际应用价值。Due to the difficult defect detection and the low detection accuracy of down-proof fabric under the condition of uneven light,uneven fabric and no obvious defect features,an algorithm for anti-noise down-proof fabric defect detection algorithm is proposed.First,RGB image is transformed into gray image,the base matrix is then constructed and its regional mean value is calculated,and the regional difference matrix is calculated.Then the binary image is obtained by comparing the elements in the difference matrix and the defined defect factor.Finally,the noise interference is eliminated by median filtering.The experiment of 3048 samples shows that the detection accuracy of down-proof fabric is over 92.7%,and the error detection rate is less than 6.9%.The algorithm,suitable for non chromatic defect detection,can accurately segment the surface of the down-proof fabric under noise conditions with better anti-noise ability,which has practical application value for anti-feather detection.

关 键 词：防羽布 噪声干扰 织物疵点检测 差异矩阵 疵点因子 中值滤波 

分 类 号：TS107[轻工技术与工程—纺织工程] TP391.41[轻工技术与工程—纺织科学与工程]