基于二维高斯核密度估计的有色纤维颜色特征提取方法  

Color feature extraction of colored fibers based on two-dimensional Gaussian kernel density estimation

作　　者：裘柯槟 陈维国[2,3] 张志强 黄为忠 QIU Kebin;CHEN Weiguo;ZHANG Zhiqiang;HUANG Weizhong(School of Fashion and Design,Jiaxing Nanhu University,Jiaxing,Zhejiang 314001,China;College of Textile Science and Engineering(International Institute of Silk),Zhejiang Sci-Tech University,Hangzhou,Zhejiang 310018,China;Zhejiang Sci-Tech University Tongxiang Research Institute,Jiaxing,Zhejiang 314500,China;Zhejiang Houyuan Textile Co.,Ltd.,Jiaxing,Zhejiang 314511,China)

机构地区：[1]嘉兴南湖学院时尚设计学院,浙江嘉兴314001 [2]浙江理工大学纺织科学与工程学院(国际丝绸学院),浙江杭州310018 [3]浙江理工大学桐乡研究院有限公司,浙江嘉兴314500 [4]浙江厚源纺织股份有限公司,浙江嘉兴314511

出　　处：《纺织学报》2024年第5期85-93,共9页Journal of Textile Research

摘　　要：为提高基于显微高光谱成像的有色纤维颜色测量的准确性和可重复性,研究了一种基于二维高斯核密度估计的有色纤维颜色特征提取方法。首先通过显微高光谱成像测色系统采集有色纤维的高光谱图像,选择400~700 nm、波段间隔为10 nm的光谱反射率,将其转换为色度值CIE L^(*)a^(*)b^(*),计算纤维区域中的颜色均值与每个像元颜色的色差ΔE_(00),建立色差ΔE_(00)与L^(*)相关联的二维数据;再基于二维高斯核密度估计方法计算像元的密度值,并确立了有色纤维的密度截断阈值估计方法,用于截断舍弃低密度的离散异常像元;最后根据像元的密度值计算加权光谱反射率并转换为相应的色度值。选取有色羊毛纤维进行实证分析,结果表明:影响颜色测量结果准确性和可重复性的离散异常像元主要存在于二维空间密度分布中的“尾部”区域,离散异常像元越多,“尾部”越长,对测量结果影响越严重;相比均值法和明度加权法,本文通过截断舍弃离散异常像元以减小其对测色结果影响的方式,提高了有色羊毛纤维颜色测量的准确性,且测量结果的可重复性最优,在有色羊毛纤维的染配色和混配色预测模型研究中具有实际应用价值。Objective The diameters of the textile fibers are usually micrometer-grade,making it difficult to directly measure the colors of the textile fibers.A non-destructive and push-broom microscopic hyperspectral imaging system consisting of a stereomicroscope,an imaging spectrograph,and a digital detector shows an excellent spatial resolution for color measurement of colored textile fibers.In order to improve the accuracy and repeatability of the microscopic hyperspectral imaging system for colored textile fibers,a color feature extraction method of colored textile fibers based on two-dimensional Gaussian kernel density estimation was proposed.Method The microscopic hyperspectral images of colored fibers were acquired by the microscopic hyperspectral imaging system.After preprocessing the hyperspectral images to obtain the spectral reflectance at 10 nm intervals over 400 to 700 nm,the fiber region of interest was chosen by the remote sensing image processing software(ENVI 4.8).The spectral reflectance was converted to chromatic values CIE L^(*)a^(*)b^(*),and theΔE_(00)between the average color and each pixel color in the fiber region was computed.A two-dimensional relationship was established between the color differenceΔE_(00)and L^(*)in the textile fiber area to estimate the density value based on the two-dimensional Gaussian kernel density.In addition,a density threshold estimation method was proposed to truncate and remove low-density outliers.Finally,the weighted spectral reflectance with the corresponding density was converted to the colorimetric values.Results Empirical analysis was performed using different colored wool fibers.The experimental results showed that the outliers(such as dust and highlight pixels)mainly existed in the tail in the two-dimensional spatial density distribution region,and the long tail indicated more outliers,which would result in a more serious impact on the accuracy and repeatability of color measurement results.In general,the relationship between L^(*)and threshold T was similar

关 键 词：有色纤维 显微高光谱成像 颜色测量 核密度估计 颜色特征提取 

分 类 号：TS101.8[轻工技术与工程—纺织工程]