The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON COMPUTERS
Transactions ID Number: 32-519
Full Name: Chun-Cheng Lin
Position: Assistant Professor
Age: ON
Sex: Male
Address: No.35, Lane 215, Sec. 1, Jhongshan Rd., Taiping City, Taichung County 411
Country: TAIWAN
Tel: Tel:+886-4-2392-4505 ext 7238
Tel prefix:
Fax: Fax: :+886-4-2392-4419
E-mail address: cclin@ncut.edu.tw
Other E-mails:
Title of the Paper: texture defect detection system with image deflection compensation
Authors as they appear in the Paper: Chun-cheng Lin, Cheng-yu Yeh
Email addresses of all the authors: cclin@ncut.edu.tw, cy.yeh@ncut.edu.tw
Number of paper pages: 11
Abstract: The image textural analysis technology has been widely used in the design of automated defect detection system. Because the presence of defects may change image textural features, a reference image without defect can be used to compare with the test image to detect whether there is any defect. However, besides defect, the deflection of the input test image could also change textural features. When there is any angular difference between the reference image and the test image, their textural features would also be different, even if there is no defect in the test image. As a result, misjudgement of the defect detection system may occur. Most of previous studies focused on the development of texture analysis technology which could decrease the effect of test image deflection. This study aimed to estimate the deflection angle of test image through polar Fourier transform and phase correlation analysis, and rotate the reference image by the same angle to compensate the!
deflection of test image. After angles of reference image and test image became the same, the textural analysis based on the gray level co-occurrence matrix was applied to analyze and compare the textural features between the reference image and the test image. The results of actual texture defect detection demonstrated that, the angular difference between the reference image and the test image could be estimated correctly, the estimation error of which was only 0¢X to 0.5¢X. By compensating the deflection of test image, the accuracy of texture defect detection could be enhanced effectively.
Keywords: Texture defect detection, Image deflection compensation, Polar Fourier transform, Phase correlation analysis, Gray level co-occurrence matrix
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 114.43.197.74
