A method to evaluate the diameter of carded cotton yarn using image processing and artificial neural networks

Abstract

Cotton yarn diameter is an important characteristic that reflects the quality of the yarn to a large extent. In this paper, a new method was proposed to determine the diameter of cotton yarn using digital image processing and artificial neural networks. After processing scanned yarn image, the inputs of ANN were represented by yarn count and the white pixels number of edge detection of processed image. The output of ANN was the diameter of cotton yarn. This ANN has been tested on new samples. The results were compared with actual results as well as both empirical formulas (Peirce’s method and Mogahzy’s method) of yarn diameter which is allocated to calculate the diameter of cotton yarn. ANN has given more acceptable results than both Peirce’s relationship and Mogahzy’s relationship. To deal easily with the algorithm of this research, a simple graphical user interface has been established.

Keywords:

• Evaluation cotton yarn diameter
• artificial neural networks (ANNs)
• image processing (IP)
• edge detection
• graphical user interface (GUI)

Disclosure statement

No potential conflict of interest was reported by the author(s).