基于混合色彩空间独立特征的色纺面料颜色表征模型

Color representation model for pre-colored fiber blends based on independent component features from mixed color space

为解决色纺加工中染色纤维整体呈色特性难以准确描述的问题,建立了基于混合色彩空间的独立特征颜色分析模型。对Lab与HSV 2种颜色空间中具有相同属性的颜色分量进行独立融合,并构建混合色彩空间;在此基础上,分别采用三阶颜色矩和局部纹理统计特征对色纺织物图像的颜色信息进行表征与融合。结果表明:对于色纺针织物或梭织物而言,所建立的颜色表征模型不仅能够对较大范围内的质量配比变化进行有效表征,而且对于染色纤维细微调整而导致的颜色改变亦能准确表达,具有理想的鲁棒性与普适性。

In order to solve the problem that the overall coloration of dyed fibers in color spinning is difficult to describe accurately, an independent feature color analysis model based on mixed color space was established. The feature color analysis model was used to independently fuse the color components with the same properties in the two color spaces of Lab and HSV (hue saturation value), and construct a mixed color space. On this basis, third-order color moments and local texture statistical features were used to characterize and fuse the color information of the colored spun fabric images. Experimental results indicate that for the colored spun knitted fabrics and woven fabrics, the established color characterization model can not only effectively characterize the mass ratio change in a large range, but also accurately express the colorimetric index caused by the tiny adjustment of the dyed fiber, and the model has ideal robustness and generality.