Defect detection in textured surfaces using color ring-projection correlation

Authors:
Du-Ming Tsai;Ya-Hui Tsai
Affiliations:
Department of Industrial Engineering and Management, Yuan-Ze University, Chungli, Taoyuan, Taiwan, Republic of China;Department of Industrial Engineering and Management, Yuan-Ze University, Chungli, Taoyuan, Taiwan, Republic of China
Venue:
Machine Vision and Applications
Year:
2003

Citing 8
Cited 2

Texture Measures for Carpet Wear Assessment

IEEE Transactions on Pattern Analysis and Machine Intelligence
Texture analysis and discrimination in additive noise

Computer Vision, Graphics, and Image Processing
Color indexing

International Journal of Computer Vision
An efficient topological characterization of gray-levels textures, using a multiresolution representation

Graphical Models and Image Processing
Multiresolution Color Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Markov Random Field Models for Unsupervised Segmentation of Textured Color Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Computing illumination-invariant descriptors of spatially filtered color image regions

IEEE Transactions on Image Processing
Unsupervised texture segmentation of images using tuned matched Gabor filters

IEEE Transactions on Image Processing

Product quality on-line inspecting for the pressed protuberant character on a metal tag

Image and Vision Computing
Defect detection in random colour textures using the MIA t2 defect maps

ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a correlation scheme that incorporates a color ring-projection representation for the automatic inspection of defects in textured surfaces. The proposed color ring projection transforms a 2-D color image into a 1-D color pattern as a function of radius. For a search window of width W, data dimensionality is reduced from O(W2) in the 2-D image to O(W) in the 1-D ring-projection space. The complexity of computing a correlation function is significantly reduced accordingly. Since the color ring-projection representation is invariant to rotation, the proposed method can be applied for both isotropic and oriented textures at arbitrary orientations. Experiments on regular textured surfaces have shown the efficacy of the proposed method.