第3期 宋强等:基于结构谱的中厚板表面缺陷识别方法 .345. 57 [7]Haralick R M.Shanmugam K.Dinstein I.Texture features for [4]Gonzalez RC,Woods R E.数字图像处理.2版.阮秋琦,阮宇 image classification.IEEE Trans Syst Man Cybern.1973.3: 智,译.北京:电子工业出版社,2003 610 [5]OjalaT.Pietiknen M.Maenpia T.Multiresolution gray scale [8]Laws K L.Texture Image Segmentation [D].University of and rotation invariant texture analysis with local binary patterns. Southern California:1980 IEEE Trans Pattern Anal Mach Intell.2002.24(7):971 [9]朊秋琦.数字图像处理学.北京:电子工业出版社,2001:419 [6]Ojala T,Valkealahti K,Oja E.et al.Texture discrimination [10]Chen D R.Chang R F.Chen CJ.et al.Classification of breast with multi-dimensional distributions of signed gray level differ uhtrasound images using fractal feature.JClin Imag.2005.29. ences.Pattern Recognit.2001.34:727 235 Recognition of surface defects on medium and heavy plates based on structure spec- trum SONG Qiang2),XU Ke),XU Jinwu3) 1)National Engineering Research Center for Advanced Rolling Technology.University of Science and Technology Beijing.Beijing 100083.China 2)Department of Mechanical and Electronic Engineering.China University of Petroleum (Beijing),Beijing 102249.China 3)Mechanical Engineering School.University of Science and Technology Beijing.Beijing 100083.China ABSTRACI In surface inspection of medium and heavy plates,defects recognition based on texture analysis suffers from mutative illuminations and scales.An illumination invariant texture analysis method named struc- ture spectrum was proposed and applied to recognition of surface defects on medium and heavy plates.Compared with other textural features such as gray level co-occurrence matrix,Laws texture energy,and Fourier power spectrum,higher classification rates were made by structure spectrum for classification of pits,scars and inclu- sions KEY WORDS medium and heavy plate;surface inspection;structure spectrum;texture analysis57 [4] Gonzalez R CWoods R E.数字图像处理.2版.阮秋琦阮宇 智译.北京:电子工业出版社2003 [5] Ojala TPietikäinen MMäenpääT.Multiresolution gray scale and rotation invariant texture analysis with local binary patterns. IEEE Trans Pattern Anal Mach Intell200224(7):971 [6] Ojala TValkealahti KOja Eet al.Texture discrimination with mult-i dimensional distributions of signed gray level differences.Pattern Recognit200134:727 [7] Haralick R MShanmugam KDinstein I.Texture features for image classification.IEEE Trans Syst Man Cybern19733: 610 [8] Laws K L.Texture Image Segmentation [ D ].University of Southern California1980 [9] 朊秋琦.数字图像处理学.北京:电子工业出版社2001:419 [10] Chen D RChang R FChen C Jet al.Classification of breast ultrasound images using fractal feature.J Clin Imag200529: 235 Recognition of surface defects on medium and heavy plates based on structure spectrum SONG Qiang 12)XU Ke 1)XU Jinw u 3) 1) National Engineering Research Center for Advanced Rolling TechnologyUniversity of Science and Technology BeijingBeijing100083China 2) Department of Mechanical and Electronic EngineeringChina University of Petroleum (Beijing)Beijing102249China 3) Mechanical Engineering SchoolUniversity of Science and Technology BeijingBeijing100083China ABSTRACT In surface inspection of medium and heavy platesdefects recognition based on texture analysis suffers from mutative illuminations and scales.An illumination invariant texture analysis method named structure spectrum was proposed and applied to recognition of surface defects on medium and heavy plates.Compared with other textural features such as gray level co-occurrence matrixLaws texture energyand Fourier power spectrumhigher classification rates were made by structure spectrum for classification of pitsscars and inclusions. KEY WORDS medium and heavy plate;surface inspection;structure spectrum;texture analysis 第3期 宋 强等: 基于结构谱的中厚板表面缺陷识别方法 ·345·