Spatial Filtering with Multi-scale Segmentation Based on Gaussian Function

作者: Chi-Fan Chen , Chia-Hsin Liang

DOI: 10.1007/978-3-540-89646-3_79

关键词: Computer visionSpatial filterVignettingSpatial frequencyMathematicsArtificial intelligenceGaussian functionImage processingSegmentationGaussian blurGaussian

摘要: This research mainly focuses in developing the algorithm for vision inspection inside TFT-LCD panels. The purpose of this is to extract defects precisely from source images with regular patterns and falloff illumination caused by vignetting effect. Specific spatial masks are generated Gaussian function means concept normal distribution. image decomposed into different frequencies scale-space representation. experimental result shows that defect can be effectively segmented smallest size less than 0.5pixel. optimized also provided paper shortening process time meet industrial needs AOI equipment. provides a novel complete solution scale manipulation processing.

参考文章(11)
Steven L. Eddins, Rafael C. Gonzalez, Richard E. Woods, Digital Image Processing Using Matlab ,(2006)
Du-Ming Tsai, Shia-Chih Lai, Defect detection in periodically patterned surfaces using independent component analysis Pattern Recognition. ,vol. 41, pp. 2812- 2832 ,(2008) , 10.1016/J.PATCOG.2008.02.011
L.M. Lifshitz, S.M. Pizer, A multiresolution hierarchical approach to image segmentation based on intensity extrema IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 12, pp. 529- 540 ,(1990) , 10.1109/34.56189
W.‐H. Wang, L. L. Cowie, A. J. Barger, A near-infrared analysis of the submillimeter background and the cosmic star-formation history The Astrophysical Journal. ,vol. 647, pp. 74- 85 ,(2006) , 10.1086/505292
John R. Williams, Kevin Amaratunga, A Multiscale Wavelet Solver with O(n) Complexity Journal of Computational Physics. ,vol. 122, pp. 30- 38 ,(1995) , 10.1006/JCPH.1995.1194
D. Chetverikov, Pattern regularity as a visual key Image and Vision Computing. ,vol. 18, pp. 975- 985 ,(2000) , 10.1016/S0262-8856(00)00041-X
S.G. Mallat, A theory for multiresolution signal decomposition: the wavelet representation IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 11, pp. 674- 693 ,(1989) , 10.1109/34.192463
Frederick M. Waltz, John W. V. Miller, Efficient algorithm for Gaussian blur using finite-state machines Proceedings of SPIE - The International Society for Optical Engineering. ,vol. 3521, pp. 334- 341 ,(1998) , 10.1117/12.326976
Jarkko Vartiainen, Albert Sadovnikov, Joni-Kristian Kamarainen, Lasse Lensu, Heikki Kälviäinen, Detection of irregularities in regular patterns machine vision applications. ,vol. 19, pp. 249- 259 ,(2008) , 10.1007/S00138-007-0096-9