Phạm Thị Diệu Thúy,
Phạm Thị Diệu Thúy, Hà Minh Tuân, Xiao Changyan, Lương Thị Thanh Xuân, Nguyễn Thị Việt Hương
In the manufacturing field of sheet products, such as paper, cigarette package, packing box, printed circuit board (PCB), solar silicon chip and so on, the detection of laminated sheet is an essential part. The precision of the counting directly affects the economic benefit of the factory and the subsequent production operation. In order to reduce the high cost and noise in mechanical paper counters, paper counting algorithms based on the gray value difference of paper have been applied and tested to solve these problems based only on vision signals. After the images graying of neatly arranged, with improvements to the greyscale edge of the Gabor filter, the gray pixel curve is obtained by using grayscale differences after projecting the gray level. Based on the interval of the peaks as the location of the peak or valley can be accurately positioned after removing the peak valley disturbances. The paper count is then made according to the location marker. Counting results show that this method of counting paper can be done with simple operation, while the accurate paper counting rate reaches more than 98%.