Title :
Research of printing ink quantity real-time detection system
Author :
Ma, Qianli ; Tang, Wanyou ; Xu, Min
Author_Institution :
Tianjin Univ. of Sci. & Technol., Tianjin, China
Abstract :
This paper introduces a method of construct printing ink quantity real-time detection system based on machine vision and digital image processing, describes the principle used in this system, highlights the problems encountered in the process of image analysis, and presents feasible ways to solve these problems. We captured the presswork images by a linear CCD camera and obtained their pixel RGB values. Then convered these RGB values to Lab values and input them into a trained neural network which outputs the ink quantity.
Keywords :
CCD image sensors; computer vision; image colour analysis; neural nets; printing industry; production engineering computing; quality control; charge-coupled device camera; digital image processing; image analysis; linear CCD camera; machine vision; neural network; pixel RGB value; printing ink quantity; quantity realtime detection system; red-green-blue value; Cameras; Charge coupled devices; Digital images; Image color analysis; Ink; Printing; Software; image analysis; neural network; printing ink quantity; programing; real-time detection;
Conference_Titel :
Image and Signal Processing (CISP), 2011 4th International Congress on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-9304-3
DOI :
10.1109/CISP.2011.6100632
