基于光谱分析的棉花异性纤维最佳波段选择方法

图像采集是基于计算机视觉的棉花异性纤维检测计量系统中的基础环节。为构建有效的图像采集系统以便检测皮棉中的异性纤维并识别其种类，在对棉纤维和异性纤维进行光谱分析的基础上，根据二者的漫反射光谱差异，提出了基于反射差极值分布的最佳检测波段选择方法和基于光谱可区分度的最佳可区分波段选择方法。光谱分析结果表明，紫外波段是带荧光异性纤维的最佳检测波段，可见光波段是带颜色异性纤维的最佳检测波段，而红外波段是塑料薄膜、毛发、羽毛等的最佳检测波段，并初步认定780～1 800 nm的近红外波段为异性纤维间的最佳可区分波段。

Selection of optimal band for detecting foreign fibers in lint cotton using spectroscopic analysis

Image acquisition is the key technique in a computer vision-based system for the inspection of foreign fibers in lint cotton and the measurement of their contents. To construct an efficient image acquisition system for the detection and classification of those foreign fibers, spectroscopic analysis of cotton fiber and foreign fibers was performed. To detect the foreign fibers effectively, a method for selecting optimal detection bands was proposed based on the extrema distribution of reflectance differences between cotton fiber and foreign fibers. An optimal distinguishing band selection method was presented in terms of the spectrum distinguishable degree. The results indicate that the ultraviolet band is the optimal band to detect the fluorescent foreign fibers, the visible light band is the optimal one to detect color foreign fibers, and the infrared band is fit for inspecting those foreign fibers such as polypropylene and polyethylene materials, candy wrappers, hairs and feathers. The infrared band of 780-1 800 nm is optimal for distinguishing these foreign fibers.