Sorting Technique of Cells in Gravure Cylinder Based on Perceptrons Network

Abstract

This work presents a new class of models for detection technique of cells in gravure cylinder. We apply perceptrons network that belongs to a model of neural network to build up a sorting system of cells in gravure cylinder. Firstly, the cells images are gained in the images capturing device. We have applied the MATLAB image processing software to read the experiment images and histogram equalization. The edge of cells is extracted by using of Sobel operator and Canny operator. We use different thresholds and experimental sigma values that compare to experimental results. It is found that extraction using the Canny operator is better than Sobel operator. Canny edge extraction operator is best when the value of sigma is 16. According to the image used in this research to determine the standard cells carving the value of gaps d0 equals 125, the value of dark tone s0 equals 394, so its standard value of gaps and dark tone are d0 ± 10 and s0 ± 10. The value of gravure outlets gaps and dark tone are measured, while d and s is in the scope of standard range, which the output 1 of the cells determined to pass and the output 0 deemed to fail. Binarization images are obtained through adaptive threshold segmentation, which regards the value of gaps and dark tone as the characteristic value when they start to sorting. Finally, we classify the cells into two classes by using perceptrons network. The experimental results consider neural network model that produce properly sorting and gain true systematization consequences by use of perceptrons network.