Color-defect classification for printed-matter visual inspection system

I. Ishimaru1, S. Hata1, M. Hirokari2
1Department of Intelligent Mechanical System Engineering Faculty of Engineering, Kagawa University, Takamatsu, Japan
2FUTEC, Inc., Takamatsu, Japan

Tóm tắt

An automatic defect classification method that pays attention not only to shape-defects but also to color-defects as well is proposed for a printed-matter visual-inspection device. The required characteristic of the shape-defect classification is to have an automatic select function of the feature variable which removes the unnecessary characteristics-parameter space to use few learning data efficiently. The characteristic of the color-defect classification is to identify an abnormal printing-device roller such as rotary press based on the color difference signal with the background color and the UCR process. We evaluated the proposed method with good result.

Từ khóa

#Inspection #Printing #Shape #Intelligent systems #Mechanical systems #Systems engineering and theory #Color #Ink #Signal processing #Graphics

Tài liệu tham khảo

ishimaru, 2000, 2-way Illumination Comparative Discrimination Method between Scratch and Particle for CMP Inspection System, Proceedings of the 6th Korea-Japan Workshop on Computer Vision (FCV 2000), 21 prunomo, 1998, Identification of color uniformity defect on the electronic displays by learning the human perception records, T IEE Japan, 118 c, 1164 asano, 1998, Progress on Kansei measurement technology and its application to visual inspection, Int J Japan Soc Prec Eng, 32, 85 asano, 1991, Learning of color uniformity grade on electronic displays, T IEE Japan, 121 c, 1395