基于Transformer网络特征融合的色纺织物颜色表征模型

Color characterization model of colored fabric based on Transformer network feature fusion

针对色纺织物特有的呈色结构以及常用单一颜色测量工具导致的数据特征局限的问题,基于Transformer网络建立多源异构数据融合颜色表征模型。从分光计数据与图像数据中分别提取光谱特征与纹理特征,使用Transformer网络融合多源异构数据特征,充分利用其互补特性,有效完备地表征色纺织物颜色信息。结果表明,本文构建的颜色表征模型能够对在较大变化范围内的染色纤维质量配比差异和由于染色纤维表面不均匀分布的颜色变化进行有效表征;在分光光度仪6、10和25 mm测量孔径下,融合特征差异与纤维配比差异的相关系数均高于85%;相较于单一光谱特征和单一图像特征,本文方法的相关系数提升10%以上,具有理想的鲁棒性。

To address the unique color structure of colored fabric and the limitations of commonly used single color measurement tools,a multi-source heterogeneous data fusion color representation model was established based on Transformer network.Spectral and texture features was extracted from spectrometer data and image data respectively,Transformer network was used to fuse multi-source heterogeneous data features,their complementary characteristics was fully utilized,and the color information of colored fabric was effectively and comprehensively characterized.The results indicate that the color characterization model constructed in this article can effectively characterize the differences in the quality ratio of dyed fibers within a large range of changes and the color changes due to uneven distribution on the surface of dyed fibers.At the same time,under the measurement aperture of 6mm,10mm,and 25mm,the correlation coefficients between the fusion feature difference and the fiber ratio difference are all higher than 85%.Compared with a single spectral feature and a single image feature,the correlation coefficient of this method is improved by more than 10%,which has ideal robustness.