A Fast Processing Approach of Cotton Foreign Fiber Images

作者：Wang, Jinxing; Wang, Qinxiang; Wang, Rui; Gao, Lijuan; Cui, Wei; Liu, Shuangxi^*

来源：Sensor Letters, 2013, 11(6-7): 1094-1099.

DOI：10.1166/sl.2013.2886

• Cotton
• Foreign Fibers
• Saturation Image
• Image Enhancement
• Image Segmentation

Foreign fibers in cotton have largely affected the final cotton textile products. The identification of foreign fibers is one of the key techniques in the automated visual inspection; image segmentation is crucial in this identification process. This paper proposes a new approach for fast segmentation of foreign fibers in cotton on the basis of enhanced saturation images. This approach includes three main steps, namely, image transformation, image enhancement and image segmentation. First, original images were converted from RGB color space to HSV color space, and then saturation images were isolated. Second, the histograms of the saturation images were analyzed, and a piecewise nonlinear transform model was proposed to enhance the image based on the analysis results. Third, the threshold value was automatically selected with improved Otsu's method. The results show that the algorithm has high speed, accuracy, anti-interference and other qualities.

• 出版日期2013-7
• 单位山东农业大学