基于智能方法的丝状异纤分离关键技术研究

针对异纤分离器存在的主要问题，指出提高异纤的检出率需要采取的综合措施，提出了异纤分离判断和评价的指标及计算、考核、测试方法，基于智能方法研究清除头发丝等难以分离异纤的关键技术，提出了基于多尺度小波和模糊方法的棉花异纤检测算法。首先对图像进行多尺度小波变换，旨在检测各类异性纤维的线爷边缘。把线条边缘的尺寸映射到隶属度空间，对隶属度求和，与阈值比较完成线务识别，可以抑制棉花图像纹理的干扰。实践证明，该算法较之常规识别算法能够较好识别丝状异纤，满足了工业的需要。

Study on Thread Foreign Matter Separation Key Technology Based on Intelligent Method

Efficient separation of cotton foreign fiber is an important and difficult task in spinning industry.For the main problems of foreign matter separator.This paper proposes cotton foreign fiber detection arithmetic based on multi-scale wavelet transform and fuzzy methods.Firstly,the image is executed through multi-scale wavelet transform in order to detect the line edge of foreign fiber.Then the size of line edge is mapped to membership space.The line edge recognition is carried out through compares the sum of all memberships with threshold value.This method can restrain the interference of cotton image texture.The practice proves this arithmetic meets the need of industry.