Abstract
In machine-vision-based systems for detecting foreign fibers, due to the background of the cotton layer has the absolute advantage in the whole image, while the foreign fiber only account for a very small part, and what’s more, the brightness and contrast of the image are all poor. Using the traditional image segmentation method, the segmentation results are very poor. By adopting the maximum entropy and genetic algorithm, the maximum entropy function was used as the fitness function of genetic algorithm. Through continuous optimization, the optimal segmentation threshold is determined. Experimental results prove that the image segmentation of this paper not only fast and accurate, but also has strong adaptability.
Highlights
The foreign fibers in cotton refer to those non-cotton fibers and dyed fibers, such as polypropylene fiber silk, hemp, feathers, colored line, colored cloth, hairs and so on
Though very low content of foreign fibers in cotton, the presence of foreign fibers will seriously affect the quality of the final cotton textile products, as they may debase the strength of the yarn, they are not easy to be dyed, and this will lead to great economic loss for the cotton textile enterprises [1]
According to the means of image segmentation, the image segmentation method can be divided into threshold method, boundary detection method, area method and so on
Summary
The foreign fibers in cotton refer to those non-cotton fibers and dyed fibers, such as polypropylene fiber silk, hemp, feathers, colored line, colored cloth, hairs and so on. Fast and accurate measurement of foreign fibers in lint cotton enterprises is an urgent problem. Using machine vision technology to identify and measure the foreign fiber is an effective and feasible solution. The basis and key of the measurement of the foreign fiber content is the foreign fiber’s classification, and the image segmentation is the premise and guarantee of the classification of the foreign fiber. Image segmentation is one of the primary stages in image processing and machine vision system, and it is the precondition of image analysis. Due to the characteristics of clear physical meaning, obviously effect, implementing and good real-time, the threshold method became one of the most commonly used image segmentation method in image analysis, image recognition and machine vision systems. The entropy of the target region and the background region are respectively defined as: t −1
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
