一种测定羊绒颜色纯度的计算机视觉系统

Computer vision system for inspection of cashmere coloured fibers

传统测定羊绒纯度的手工方法受主观因素影响,精度和速度不能满足生产需要。文章提出了一种由纤维分匀器、图像获取系统和图像处理计算机组成的、能客观测定羊绒颜色纯度的计算机视觉系统。由实验结果的对比可以看出本系统的研究成果是可行的。文章还对系统采用的检测样品的预处理、羊绒中杂色毛的识别与评定算法等关键技术进行了重点介绍。

The traditions/ method for the evaluation of cashmere quality is subjective so the accuracy and speed cannot satisfy the production. In this paper, a computer vision system is presented for the objective identification and classification of pigmented fibers in cashmere. The system consists of a web maker, an image acquisition system and a computer for image processing. The cashmere or wool can be opened out into a thin fiber web by the web maker, an image acquisition system consists of adocument Scanner or s small conveyor and a linescan colour CCD camera, algorithm for image processing contains ＂threshold＂method, ＂dilation＂ method, ＂thinning＂ method, etc. Aaccording to the result of the experiment, the system is feasible. The techniques of fiber preparation, image acquisition and the development of suitable algorithms together with software for detection and counting of pigmented fibers are described in detail.