Research on image recognition method of foreign fibers in lint

This paper proves the property of Otsu algorithm is equally applicable to two-dimensional Otsu algorithm, the property is that the threshold value of the Otsu method is the average of the means of two classes partitioned by this threshold. On the basis of this property, two-dimensional Otsu method is improved into an iterative method firstly, which reduces the time consumption greatly. Secondly, this paper proposes a twice segmentation method to recognize translucent foreign fibers which are undetectable reasonably for now, such as gray polypropylene yarn. Experimental results show that, ensured the meet of real-time, the overall detect rate is up to 94.7%, this research has high practical value.