板带钢缺陷图像的多体分类模型及识别技术研究
|
摘要
随着市场变化及其结构的调整,高品质的板带钢在钢铁工业中的地位日益重要。它在汽车、家电、造船、航空航天等相关领域有重要应用并且需求量上升迅猛。由于连铸钢坯、轧制设备、加工工艺等多方面的原因,会导致板带钢表面出现焊缝、夹杂、抬头纹、氧化皮、结疤、辊印、刮伤等多种类型的缺陷。这些缺陷的存在,一方面降低了产品的抗腐蚀性、耐磨性和疲劳强度等性能,另一方面也使其无法应用于外观要求较高的领域。虽然我国的钢铁产量居世界第一,但每年却需要大量进口高品质的钢板。提高板带钢表面缺陷的检测与控制水平,具有重要的战略意义。
模式识别是基于图像信息的检测技术的重要步骤。目前应用于板带钢表面缺陷检测系统的模式识别方法存在环节众多、识别率低、识别速度较慢、推广性差、适应性差等不足。其原因主要在于:就研究对象的特征而言,一方面不同类缺陷的图像在特征上并不存在很明确的界限,另一方面,同一类缺陷的图像在特征上存在较大差异;就常用模式分类方法而言,其分类机制与特征空间中类别的分布特性在表现方式、尺度、扩张性等方面存在的多种不一致,产生了聚类中心周围含有其它类别杂点、拟合划分面切开同类样本等问题,增加了误识的可能。对于以上存在的问题,可以通过构建适应性良好的分类模型加以解决。因此,本文在分类模型及具体的分类器实现方法上展开研究,具体研究内容和取得成果如下:
(1)对模式分类机制进行深入研究,总结分析目前常用的分类方法存在的问题。针对这些问题,提出类别的本征空间和认知空间的概念,进而提出与类别在认知空间的分布状态的一致性较好的以多个单一类别的扩张体为基本元素的多体分类模型,给出了该模型的具体构建方法。通过理论分析和实例分析表明该模型与常用方法相比的在分类机制上优越性。
(2)结合多体分类模型,对传统SOFM神经网络进行改进和优化,提出了WTM-SOFM分类法。该方法采用跟踪SOFM网络训练历史轨迹的方式克服了SOFM神经网络对类别间隔狭小或空间怠点分类能力的不足。实验研究表明它相比SOFM具有更强的边界冲突调解及边界扩张能力。
(3)研究并提出一种新的模式分类方法,即版图分类法。该方法受到人类历史上版图形成过程中多体划分效果的启发,结合多体分类模型的要求而构建。与WTM-SOFM方法相比,它对未知分类空间的估计划分更具合理性。实例分析表明,在众多其它方法很难解决或根本无法计算的类边界复杂交错、多尺度等分类问题上,仍然可以表现出很高的识别率和识别速度。在板带钢表面缺陷分类实验中,对六种缺陷的识别率明显高于其它常用分类方法。
As the market changes and restructuring, high-quality sheet steel in the steel industry's position is becoming increasingly important. Its comsuption rapidly increasing in automotive, home appliance, shipbuilding, aerospace and other important applications concerned. As results coming from continuous casting billets, rolling equipment, relavent process, and many other reasons, there are weld, inclusion, wrinkles, scale, roller mark, scratches and various defects in strip surface. With these defections, the corrosion resistance, wear resistance, fatigue strength and other important performance of the product is reduced; on the other hand, it can not be used in the scopes with appearance quality demanded any more. As the world's biggest iron and steel production country, plenty of high-quality steel strip is imported in China, every year. It becomes an important strategic significance to improve the surface quality of strip.
Pattern recognition is an important step in detection technology based on the image information. Currently pattern recognition technology which is used in strip surface defect detection system has a lot problem such as complex recognition steps, low recognition rate, slow recognition speed, weak generalization ablility, poor adaptability and so on. The reason is mainly due to: the characteristics of the study, on one side, the image of different types of defects does not exist the clear boundaries in the characteristics space, on the other hand, the character of same type of defects might be really different; on common pattern classification methods, the classification mechanism and the characteristics of classes distribution in feature space exist in a variety of inconsistent in the way of expressions, scale, expansion feature and so on which produced the problem such as the situations of miscellaneous points around the cluster center, fitting surface divided into same class samples and so on, causeing higher possibility of error. In view of the above problems, it is possible by constructing a good model of adaptive classification process to be addressed. The classification model and the specific realization of the classifier is focused on for further improvment in the study.The research content and results are as follows:
(1) Though the in-depth research of the pattern classification mechanism, the common problems and limitations of current classification methods is analysed. To solve these problems, the concept concerned classes eigen space and cognitive space are proposed, and then the multi-space classification model which has better consistency of the class distribution of cognitive space with the basic elements of many single type expansion subspace is established. The construction method is given for this model. Through theoretical analysis and case analysis shows that the superiority of the classification mechanism comparing with the common methods.
(2) According to the requirments of the mulit-space classification model, WTM-SOFM classification method is proposed as the optimization of SOFM neural network. The method used to track the training history of SOFM network approach to overcome the less capacity of SOFM neural network for classification of the situations of cramped and idel space among classes centre in the feature space. The experimental study shows that it is a classifier with more cpapcity of the conflict mediation and the border expansion compared to SOFM.
(3) proposed a new pattern classification method, namely, the territory classification method. This method is elicited from the multi-space division effect in the formation of the territory of the history of mankind, based on the request of mulit-space classification model. Comparing the method of WTM-SOFM, the division and estimation rules for the unknown classification space are more reasonable. Experimental analysis shows it can still show very high recognition rate and recognition speed on the situations of the complex boundary staggered, multi-scale and other issues which is difficult to solve or impossible to calculate for some comon ways. In the experiment of strip surface defects classification, the identification of the six defects was significantly higher than other common classification methods.
模式识别是基于图像信息的检测技术的重要步骤。目前应用于板带钢表面缺陷检测系统的模式识别方法存在环节众多、识别率低、识别速度较慢、推广性差、适应性差等不足。其原因主要在于:就研究对象的特征而言,一方面不同类缺陷的图像在特征上并不存在很明确的界限,另一方面,同一类缺陷的图像在特征上存在较大差异;就常用模式分类方法而言,其分类机制与特征空间中类别的分布特性在表现方式、尺度、扩张性等方面存在的多种不一致,产生了聚类中心周围含有其它类别杂点、拟合划分面切开同类样本等问题,增加了误识的可能。对于以上存在的问题,可以通过构建适应性良好的分类模型加以解决。因此,本文在分类模型及具体的分类器实现方法上展开研究,具体研究内容和取得成果如下:
(1)对模式分类机制进行深入研究,总结分析目前常用的分类方法存在的问题。针对这些问题,提出类别的本征空间和认知空间的概念,进而提出与类别在认知空间的分布状态的一致性较好的以多个单一类别的扩张体为基本元素的多体分类模型,给出了该模型的具体构建方法。通过理论分析和实例分析表明该模型与常用方法相比的在分类机制上优越性。
(2)结合多体分类模型,对传统SOFM神经网络进行改进和优化,提出了WTM-SOFM分类法。该方法采用跟踪SOFM网络训练历史轨迹的方式克服了SOFM神经网络对类别间隔狭小或空间怠点分类能力的不足。实验研究表明它相比SOFM具有更强的边界冲突调解及边界扩张能力。
(3)研究并提出一种新的模式分类方法,即版图分类法。该方法受到人类历史上版图形成过程中多体划分效果的启发,结合多体分类模型的要求而构建。与WTM-SOFM方法相比,它对未知分类空间的估计划分更具合理性。实例分析表明,在众多其它方法很难解决或根本无法计算的类边界复杂交错、多尺度等分类问题上,仍然可以表现出很高的识别率和识别速度。在板带钢表面缺陷分类实验中,对六种缺陷的识别率明显高于其它常用分类方法。
As the market changes and restructuring, high-quality sheet steel in the steel industry's position is becoming increasingly important. Its comsuption rapidly increasing in automotive, home appliance, shipbuilding, aerospace and other important applications concerned. As results coming from continuous casting billets, rolling equipment, relavent process, and many other reasons, there are weld, inclusion, wrinkles, scale, roller mark, scratches and various defects in strip surface. With these defections, the corrosion resistance, wear resistance, fatigue strength and other important performance of the product is reduced; on the other hand, it can not be used in the scopes with appearance quality demanded any more. As the world's biggest iron and steel production country, plenty of high-quality steel strip is imported in China, every year. It becomes an important strategic significance to improve the surface quality of strip.
Pattern recognition is an important step in detection technology based on the image information. Currently pattern recognition technology which is used in strip surface defect detection system has a lot problem such as complex recognition steps, low recognition rate, slow recognition speed, weak generalization ablility, poor adaptability and so on. The reason is mainly due to: the characteristics of the study, on one side, the image of different types of defects does not exist the clear boundaries in the characteristics space, on the other hand, the character of same type of defects might be really different; on common pattern classification methods, the classification mechanism and the characteristics of classes distribution in feature space exist in a variety of inconsistent in the way of expressions, scale, expansion feature and so on which produced the problem such as the situations of miscellaneous points around the cluster center, fitting surface divided into same class samples and so on, causeing higher possibility of error. In view of the above problems, it is possible by constructing a good model of adaptive classification process to be addressed. The classification model and the specific realization of the classifier is focused on for further improvment in the study.The research content and results are as follows:
(1) Though the in-depth research of the pattern classification mechanism, the common problems and limitations of current classification methods is analysed. To solve these problems, the concept concerned classes eigen space and cognitive space are proposed, and then the multi-space classification model which has better consistency of the class distribution of cognitive space with the basic elements of many single type expansion subspace is established. The construction method is given for this model. Through theoretical analysis and case analysis shows that the superiority of the classification mechanism comparing with the common methods.
(2) According to the requirments of the mulit-space classification model, WTM-SOFM classification method is proposed as the optimization of SOFM neural network. The method used to track the training history of SOFM network approach to overcome the less capacity of SOFM neural network for classification of the situations of cramped and idel space among classes centre in the feature space. The experimental study shows that it is a classifier with more cpapcity of the conflict mediation and the border expansion compared to SOFM.
(3) proposed a new pattern classification method, namely, the territory classification method. This method is elicited from the multi-space division effect in the formation of the territory of the history of mankind, based on the request of mulit-space classification model. Comparing the method of WTM-SOFM, the division and estimation rules for the unknown classification space are more reasonable. Experimental analysis shows it can still show very high recognition rate and recognition speed on the situations of the complex boundary staggered, multi-scale and other issues which is difficult to solve or impossible to calculate for some comon ways. In the experiment of strip surface defects classification, the identification of the six defects was significantly higher than other common classification methods.
引文
1.Badger J C,Enright S T.Automated surface inspection system[J].Iron and Steel Engineer,1996,73(3):48-51.
2.Sugimoto T,Kawaguchi T.Development of a surface defect inspection system using radiant light from steel products in a hot rolling line[J].IEEE Transactions on Instrumentation and Measurement,1998,47(2):409-416.
3.边肇祺,张学工等.模式识别(第二版)[M].北京:清华大学出版社,2000.
4.Jain A K,Duin Robert P W.Statistical pattern recognition:areview[J].IEEE Trans actions on pattern analysis and machine intelligence,2000,22(1):4-37.
5.Thomas F Porter,Robert A Sytvester,Theodore W Bouyoucas et al.Automatic strip surface defect detection system[J],Iron and Steel Engineer,1988,65(12):17-20.
6.Canella G,Falessi R.Surface Inspection and Classification Plant for Stainless Steel Strip[J],Non-Destructive Testing,1992:1185-1189.
7.SureshBR,FundakowskiRA,LevittTS,etal.A Real-time Automated Visual Inspection System for Hot Steel Slabs[J],IEEETrans.PatternAnal.MachineIntell,1983,5(6):563-572.
8.胡亮,段发阶,丁克勤,雷永强,叶声华.带钢表面缺陷计算机视觉在线检测系统的设计[J],无损检测,2003,25(6):287-291.
9.李炜,黄心汉,王敏,王国红.基于机器视觉的带钢表面缺陷检测系统[J],华中科技大学学报,2003,31(2):72-74.
10.韩崇昭,朱洪艳,段战胜等.多源信息融合[M],北京:清华大学出版社,2006.
11.陈正阁,王长龙,纪凤珠,左宪章.故障诊断中的多传感器信息融合技术[J],无损检测,2006,24(5):20-25.
12.Tekalp,Ahmet Murat.Identification and Restoration of Noisy and Blurred Images[D],Dissertation Abstracts International,1984,(B46-03):0926.
13.Angwin,Denise Louise.Adaptive image restoration using reduced-order model based Kalman filters[D],Dissertation Abstracts International,1989,(B51-01):0341.
14.Hong,Min-Cheol.Adaptive regularized image and video restoration.Dissertation Abstracts International[D],1997,(B58-11):6129.
15.Pozidis,Haralampos.Techniques for blind system identification and application to the equalization of PAM/QAM modulated signals[D],1998,Dissertation Abstracts International,(B59-0):4346.
16.屈志毅,沃淼,任志宏.基于交替迭代和神经网络的盲目图像恢复[J],计算机学报,2000,23(4):410-413.
17.李威,郁道银,谢洪波.基于邻域信息优化方法的图像恢复与增强[J],天津大学学报,200,34(4):495-498.
18.Topi Maenpaa,Markus Turtinen,Matti Pietikainen.Real-time surface inspection by texture[J],Real-Time Imaging,2003,(9):289-296.
19.Cun Lu Xu,Yan Qiu Chen.Classifying image texture with statistical landscape features[J],Pattern Analysis and Applications,2005,8(4):321-331.
20.I.B.Gurevivh,I.V.Koryabkina.Comparative analysis and classification of features for image models[J],Pattern Recognition and Image Analysis,2006,16(3):265-297.
21.R.A.Fisher.The use of multiple measurements in taxonomic problem,Annals of Eugenics[J],1936,7:179-188.
22.C.K.Chow.An optimum character recognition system using decision functions,IRE Trans.Electronic Computers[J],1957,6:247-254.
23.G.Nagy.Pattern Recognition 1966 IEEF,Workshop,IEEE Spectrum[J],1967,2:92-94.
24.K.Fukunaga.Introduction to Statistical Pattern Recognition[M],Academic Press,1972.
25.R.O.Duda,P.E.Hart.Pattern Classification and Scene Analysis[M],John Wiley & Sons,New York,1973.
26.L.A.Zadeh.Fuzzy Sets.Information control,1965,(8):338-353.
27.Boris Shukhat.Supervised fuzzy pattern recognition[J],Fuzzy Sets and Systems 1998,(100):257-265.
28.Ketty P.Finite L-fuzzy acceptors,regular L-fuzzy grammars and syntactic pattern recognition[J],Fuzziness and Knowledge-Based Systems,2004,12(1):89-104.
29.B.Samanta,K.R.Al-Balushi,S.A.Al-Araimi.Artificial neural networks and genetic algorithm for bearing fault detection.Soft Comput[J],2006,10(3):264-271.
30. B. Samanta, C. Nataraj. Surface roughness prediction in machining using Computational Intelligence[J], IJMR, 2008, 3(4): 379-392.
31. Simpson. Fuzzy min-max neural network-part1: Classification[J]: IEEE Trans on NN, 1992,3(5): 776-786.
32. Bogdan Gabrys, Andraej Bargiela. General fuzzy Min-Max neural networks for clustering and classification[J], IEEE Trans on N N, 2000,11(3):769-783.
33. Vapnik V. The Nature of Statistical Learning Theory[M]. New York: Springer-Verlag, 1995.
34. Ai H, Liang L, Xu G. Face detection based on template matching and support vector machines[J], IEEE Signal Processing , 2001,12:1006-1009.
35. Guodong Guo,Stan Z. Support vector machines for face recognition[J], Image and Vision Computing, 2001,19:631-638.
36. B.Scholkopf, A.Smola , K.R.Muller. Nonlinear Component Analysis as a Kernel Eigenvalue Problem[J],Neural Computation, 1998,10:1299-1319.
37. Francis R.Bach,Michael I.Jordan. Kernel indepent component analysis[J], Journal of Learning Research, 2002, 3:1-48.
38. Colin Campbell. Kernel methods: a survey of current techniques[J], Neurocomputing, 2000(48): 63-84.
39. K-R.Muller, S.Mika, G.Ratsch et al. An Introduction to Kernel Based Learning Algorithms. IEEE Transactions on Neural Networks, 2001,12(2): 181 -201.
40. Richard O. Duda, Peter E. Hart, David G. Stork. Pattern Classification[M].(2nd Edition), Wiley-Interscience, 2000.
41. J. Cheng, R. Greiner. Comparing Bayesian Network classifiers. Proceedings of the 15th Conference on Uncertainty in Artificial Intelligence. 1999: 101-108.
42. Song Chunyue, Song Zhihuan, Li Ping,et al.The study of Naive Bayes algorithm online in data mining. Intelligent Control and Automation, WCICA 2004. Fifth World Congress on Publication.2004,5:4323-4326.
43. P. Soucy, G.W. Mineau. A simple KNN algorithm for text categorization. Proceedings of the IEEE International Conference on Data Mining. 2001, 647-648.
44. CY Qiu, M.S. Nixon, R.I. Damper. Implementing the k-nearest neighbour rule via a neural network.Proceedings of the IEEE International Conference on Neural Networks,1995,1:136-140.
45.L.I.Kuncheva,Fitness function in editing knn reference set by genetic algorithms.Pattern Recognition.1997,30(6):1041 - 1049.
46.Kennedy,J.and R.C.Eberhart.Particle Swarm Optimization.In Proceeding of IEEE International Conference on Neural Networks(ICNN).1995.Perth,Australia.
47.R.C.,Eberhart and Kenedy J.a new optimizer using particle swarm thery in Proceeding of the Sixth International Symposium on Micro Machine and Human Science.1995.Nagoya,Japan.
48.何玉彬,李新忠.神经网络控制技术及其应用[M].北京:科学出版社,2000.
49.Paolo Gallina,Neural network painting defect classification using Karhunen-Loeve transformation[J],Optics and Lasers in Engineering,1999,32:29-40.
50.Iivarinen Jukka,Heikkinen Katriina,Rauhamaa Juhani.A Defect Detection Scheme for Web Surface Inspection[J],International Journal of Pattern Recognition &Artificial Intelligence,2000,14(6):735-756.
51.王成明,颜云辉,韩英莉等.神经网络方法在冷轧带钢表面质量检测中的应用研究[J],机械制造,2006,44(508):71-72.
52.Vapnik V.The Nature of Statistical Learning Theory[M].New York:Springer-Verlag,1995.
53.B.Samanta,K.R.Al-Balushi,S.A.Al-Araimi.Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection[J],Engineering Applications of Artificial Intelligence,2003,(16):657-665.
54.黄景涛,马龙华,钱积新.一种用于多分类问题的改进支持向量机[J],浙江大学学报(工学版),2004,38(12):1633-1636.
55.余艳芳,高大启.一种改进的最小二乘支持向量机及其应用[J],计算机工程与科学,2006,28(2):69-71.
56.C Cortes,V Vapnik.Support vector networks[J].Machine Learning,1995,20:273-297.
57.S Jacoub,Y Abdeljaoued,E Mayoraz.Fusion of face and speech data for person identity verification[J].IEEETrans on Neural Network,1999,10(5):1065-1074.
58.Shimshoni Y,Intrator N.Classification of Seismic Signals by Integrating Ensembles of Neural Networks.IEEE Transactions on Signal Processing,1998,46(5):1194-1201.
59.Kim K,Kim C.Forecasting Time Series with Genetic Fuzzy Prodictor Ensemble.IEEE Transactions on Fuzzy Systems,1997,5(4):523-535.
60.Russo A P.Constrained Neural Networks for Recognition of Passive Sonar Signals Using Shape.In:Proceedings of the IEEE Conference on Neural Networks for Ocean Engineering,1991,69-76.
61.Stamatatos E and Widmer G Automatic identification of music performers with learning ensembles[J].Artificial Intelligence,2005,(165):37-56.
62.Kim E,Kim W and Lee Y.Combination of multiple classifiers for the customer's purchase behavior prediction.Decision Support Systems,2003,34:167-175.
63.Shin H.W.and Sohn S.Y.Combining both ensemble and dynamic classifier selection schemes for prediction of mobile internet subscribers[J].Expert Systems with Application,2003,(25):63-68.
64.He C,Girolami M and Ross G.Employing optimized combinations of one-class classifiers for automated currency validation.Pattern Recognition,2004(37):1085-1096.
65.Yu K,Jiang X and Bunke H.Lipreading:A classifier combination approach.Pattern Recogition Letters[J],1997,18(1.1):1421-1426.
66.路志英,赵智超,郝为.基于人工神经网络的多模型综合预报方法[J],计算机应用,2004,24,(4):50-52.
67.刘伟嵬,颜云辉,孙宏伟.一种基于邻域噪声评价法的图像去噪算法[J],东北大学学报,2008,29(7):1033-1036.
68.王永慧,颜云辉,梁惠升.带钢表面缺陷图像小波融合方法[J],东北大学学报,2009,30(5):733-737.
69.E.Mjolsness and D.DeCoste.Machine Learning for Science:State of the Art and Future Prospects.Science[J].2001,(293):2051-2055.
70.B.Scholkopf,A.Smola.Nonlinear component analysis as kernel eigenvalue problem,Neural Computation[J],1998,10(5):1299-1319.
71.王旭,王宏,王文辉.人工神经元网络原理与应用[M],沈阳:东北大学出版社, 2000.
72. Shin H.W. and Sohn S.Y. Combining both ensemble and dynamic classifier selection schemes for prediction of mobile internet subscribers[J]. Expert Systems with Application,2003, (25):63-68.
73. T. Kohonen, K. Torkkola, M. Shozakai, J. Kangas, O.Venta, Microprocessor implementation of a large vocabularyspeech recognizer and phonetic typewriter for Finnishand Japanese, Proceedings of the European Conference ofSpeech Technology, Edinburgh, 1987, 2377-2380.
74. T. Kohonen, Self-organizing maps of symbol strings[J], Neurocomputing, ELSEVIER, 1998, 19-30.
75. D.H. Graf, W.R. Lalonde, Neuroplanners for hand/eye coordination, Proceedings of the International Joint Conference on Neural Networks, Washington, 1989, 543 -548.
76. I.K. Sethi , I. Coman. Image retrieval using hierarchical self-organizing feature maps[J], Pattern Recognition Letters, Elsevier Science Inc, New York, 1999, pp. 1337-1345.
77. Z.li -Zhang, S.Sheng-he, Z. Fu-chun, etc. Image fusion based on median filters and SOFM neural networks: a three-step scheme, Signal Processing, EURASIP, 2001, 1325-1330.
78. X.Jian-qiao, L.bin Z.Yong-heng. Automatic classification of stellar spectra using the SOFM method[J], Chinese Astronomy and Astrophysics, Beijing, 2001, 120-131.
79. F. Sebelius, L. Eriksson, H. Holmberg, A. Levinsson, etc. Classification of motor commands using a modified self-organising feature map [J], Medical Engineering & Physics, IPEM, 2005, 403-413.
80. A. Laha, R. Nikhil Pal. Dynamic generation of prototypes with self-organizing feature maps for classifier design [J], Pattern Recognition, ELSEVIER, 2001, 315-321.
81. Jang Hee Lee, Sung Jin You, Sang Chan Park. A new intelligent SOFM-based sampling planfor advanced process control[J], Expert Systems with Applications, ELSEVIER, 2001, 133-151.
82. S. Patra, S. Ghosh, A. Ghosh. Unsupervised change detection in remote-sensing images using modified self-organizing feature map neural network. International Conference on Computing:Theory and Applications(ICCTA-2007),Kolkata,India,2007,716-720.
83.L.Bruzzone,D.F.Prieto.Automatic analysis of the difference image for unsupervised change detection.IEEE,2000,1171-1182.
84.T.Kohonen.Self-organized formation of topologically correct feature maps[J],Biological Cybernetics,Springer Berlin/Heidelberg,1982,59-69.
85.T.Kohonen.Fast Evolutionary Learning with Batch-Type Self-Organizing Maps[J],Neural Processing Letters,1999,153-162.
86.T.Kohonen.How to make large self-organizing maps for nonvectorial data[J],Neural Networks,2002,945-952.
87.T.Kohonen.Visual Feature Analysis by the Self-Organising Maps[J],Neural Comput & Applications,Springer-Verlag London,1998,273-286.
88.魏天宇.板带材表面缺陷组合特征的降维聚类识别算法研究[D].沈阳:东北大学,2006:21-29.
89.李骏,颜云辉,王成明等.板带材缺陷检测中的多特征优化组合方法研究[J],计算机工程与应用,2007,43(22):197-200.
90.Aitkenhead M J.A co-evolving decision tree classification method[J].Expert Systems with Applications,2008(34):18-25.
91.Arivazhagan S,Ganesan L.Texture classification using wavelet transform[J].Pattern Recognition Letters,2003(24):1513-1521.
92.Kohonen T.How to make large self-organizing maps for nonvectorial data[J].Neural Networks,2002:945-952.
93.Kohonen T.Visual Feature Analysis by the Self-Organising Maps[J].Neural Comput & Applications,1998:273-286.
94.M.Jayabharata Reddy,D.K.Mohanta.A wavelet-fuzzy combined approach for classification and location of transmission line faults[J],Electrical Power and Energy Systems,2007,29:669-678.
95.M.J.Aitkenhead.A co-evolving decision tree classification method[J],Expert Systems with Applications,2008,34:18-25.
96.Arivazhagan S,Ganesan L.Texture classification using wavelet transform[J],Pattern Recognition Letters, 2003, 24:1513-1521.
97. I.B.Gurevivh. Comparative analysis and classification of features for image models[J], Pattern Recognition and Image Analysis, 2006,16(3):265-297.
98. Joon Hur, Jong Woo Kim. A hybrid classification method using error pattern modeling[J],Expert Systems with Applications, 2008,34 : 231-241.
99. Jie Li, Xianglong Tang. A new classification model with simple decision rule for discovering optimal feature gene pairs [J], Computers in Biology and Medicine, 2007,37:1637-1646.
100. J.L. Giraudel and S. Lek. A Comparison of self-organizing map algorithm and some conventional statistical methods for ecological community ordination[J], Ecological Modelling, 2001, 146:329-339.
2.Sugimoto T,Kawaguchi T.Development of a surface defect inspection system using radiant light from steel products in a hot rolling line[J].IEEE Transactions on Instrumentation and Measurement,1998,47(2):409-416.
3.边肇祺,张学工等.模式识别(第二版)[M].北京:清华大学出版社,2000.
4.Jain A K,Duin Robert P W.Statistical pattern recognition:areview[J].IEEE Trans actions on pattern analysis and machine intelligence,2000,22(1):4-37.
5.Thomas F Porter,Robert A Sytvester,Theodore W Bouyoucas et al.Automatic strip surface defect detection system[J],Iron and Steel Engineer,1988,65(12):17-20.
6.Canella G,Falessi R.Surface Inspection and Classification Plant for Stainless Steel Strip[J],Non-Destructive Testing,1992:1185-1189.
7.SureshBR,FundakowskiRA,LevittTS,etal.A Real-time Automated Visual Inspection System for Hot Steel Slabs[J],IEEETrans.PatternAnal.MachineIntell,1983,5(6):563-572.
8.胡亮,段发阶,丁克勤,雷永强,叶声华.带钢表面缺陷计算机视觉在线检测系统的设计[J],无损检测,2003,25(6):287-291.
9.李炜,黄心汉,王敏,王国红.基于机器视觉的带钢表面缺陷检测系统[J],华中科技大学学报,2003,31(2):72-74.
10.韩崇昭,朱洪艳,段战胜等.多源信息融合[M],北京:清华大学出版社,2006.
11.陈正阁,王长龙,纪凤珠,左宪章.故障诊断中的多传感器信息融合技术[J],无损检测,2006,24(5):20-25.
12.Tekalp,Ahmet Murat.Identification and Restoration of Noisy and Blurred Images[D],Dissertation Abstracts International,1984,(B46-03):0926.
13.Angwin,Denise Louise.Adaptive image restoration using reduced-order model based Kalman filters[D],Dissertation Abstracts International,1989,(B51-01):0341.
14.Hong,Min-Cheol.Adaptive regularized image and video restoration.Dissertation Abstracts International[D],1997,(B58-11):6129.
15.Pozidis,Haralampos.Techniques for blind system identification and application to the equalization of PAM/QAM modulated signals[D],1998,Dissertation Abstracts International,(B59-0):4346.
16.屈志毅,沃淼,任志宏.基于交替迭代和神经网络的盲目图像恢复[J],计算机学报,2000,23(4):410-413.
17.李威,郁道银,谢洪波.基于邻域信息优化方法的图像恢复与增强[J],天津大学学报,200,34(4):495-498.
18.Topi Maenpaa,Markus Turtinen,Matti Pietikainen.Real-time surface inspection by texture[J],Real-Time Imaging,2003,(9):289-296.
19.Cun Lu Xu,Yan Qiu Chen.Classifying image texture with statistical landscape features[J],Pattern Analysis and Applications,2005,8(4):321-331.
20.I.B.Gurevivh,I.V.Koryabkina.Comparative analysis and classification of features for image models[J],Pattern Recognition and Image Analysis,2006,16(3):265-297.
21.R.A.Fisher.The use of multiple measurements in taxonomic problem,Annals of Eugenics[J],1936,7:179-188.
22.C.K.Chow.An optimum character recognition system using decision functions,IRE Trans.Electronic Computers[J],1957,6:247-254.
23.G.Nagy.Pattern Recognition 1966 IEEF,Workshop,IEEE Spectrum[J],1967,2:92-94.
24.K.Fukunaga.Introduction to Statistical Pattern Recognition[M],Academic Press,1972.
25.R.O.Duda,P.E.Hart.Pattern Classification and Scene Analysis[M],John Wiley & Sons,New York,1973.
26.L.A.Zadeh.Fuzzy Sets.Information control,1965,(8):338-353.
27.Boris Shukhat.Supervised fuzzy pattern recognition[J],Fuzzy Sets and Systems 1998,(100):257-265.
28.Ketty P.Finite L-fuzzy acceptors,regular L-fuzzy grammars and syntactic pattern recognition[J],Fuzziness and Knowledge-Based Systems,2004,12(1):89-104.
29.B.Samanta,K.R.Al-Balushi,S.A.Al-Araimi.Artificial neural networks and genetic algorithm for bearing fault detection.Soft Comput[J],2006,10(3):264-271.
30. B. Samanta, C. Nataraj. Surface roughness prediction in machining using Computational Intelligence[J], IJMR, 2008, 3(4): 379-392.
31. Simpson. Fuzzy min-max neural network-part1: Classification[J]: IEEE Trans on NN, 1992,3(5): 776-786.
32. Bogdan Gabrys, Andraej Bargiela. General fuzzy Min-Max neural networks for clustering and classification[J], IEEE Trans on N N, 2000,11(3):769-783.
33. Vapnik V. The Nature of Statistical Learning Theory[M]. New York: Springer-Verlag, 1995.
34. Ai H, Liang L, Xu G. Face detection based on template matching and support vector machines[J], IEEE Signal Processing , 2001,12:1006-1009.
35. Guodong Guo,Stan Z. Support vector machines for face recognition[J], Image and Vision Computing, 2001,19:631-638.
36. B.Scholkopf, A.Smola , K.R.Muller. Nonlinear Component Analysis as a Kernel Eigenvalue Problem[J],Neural Computation, 1998,10:1299-1319.
37. Francis R.Bach,Michael I.Jordan. Kernel indepent component analysis[J], Journal of Learning Research, 2002, 3:1-48.
38. Colin Campbell. Kernel methods: a survey of current techniques[J], Neurocomputing, 2000(48): 63-84.
39. K-R.Muller, S.Mika, G.Ratsch et al. An Introduction to Kernel Based Learning Algorithms. IEEE Transactions on Neural Networks, 2001,12(2): 181 -201.
40. Richard O. Duda, Peter E. Hart, David G. Stork. Pattern Classification[M].(2nd Edition), Wiley-Interscience, 2000.
41. J. Cheng, R. Greiner. Comparing Bayesian Network classifiers. Proceedings of the 15th Conference on Uncertainty in Artificial Intelligence. 1999: 101-108.
42. Song Chunyue, Song Zhihuan, Li Ping,et al.The study of Naive Bayes algorithm online in data mining. Intelligent Control and Automation, WCICA 2004. Fifth World Congress on Publication.2004,5:4323-4326.
43. P. Soucy, G.W. Mineau. A simple KNN algorithm for text categorization. Proceedings of the IEEE International Conference on Data Mining. 2001, 647-648.
44. CY Qiu, M.S. Nixon, R.I. Damper. Implementing the k-nearest neighbour rule via a neural network.Proceedings of the IEEE International Conference on Neural Networks,1995,1:136-140.
45.L.I.Kuncheva,Fitness function in editing knn reference set by genetic algorithms.Pattern Recognition.1997,30(6):1041 - 1049.
46.Kennedy,J.and R.C.Eberhart.Particle Swarm Optimization.In Proceeding of IEEE International Conference on Neural Networks(ICNN).1995.Perth,Australia.
47.R.C.,Eberhart and Kenedy J.a new optimizer using particle swarm thery in Proceeding of the Sixth International Symposium on Micro Machine and Human Science.1995.Nagoya,Japan.
48.何玉彬,李新忠.神经网络控制技术及其应用[M].北京:科学出版社,2000.
49.Paolo Gallina,Neural network painting defect classification using Karhunen-Loeve transformation[J],Optics and Lasers in Engineering,1999,32:29-40.
50.Iivarinen Jukka,Heikkinen Katriina,Rauhamaa Juhani.A Defect Detection Scheme for Web Surface Inspection[J],International Journal of Pattern Recognition &Artificial Intelligence,2000,14(6):735-756.
51.王成明,颜云辉,韩英莉等.神经网络方法在冷轧带钢表面质量检测中的应用研究[J],机械制造,2006,44(508):71-72.
52.Vapnik V.The Nature of Statistical Learning Theory[M].New York:Springer-Verlag,1995.
53.B.Samanta,K.R.Al-Balushi,S.A.Al-Araimi.Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection[J],Engineering Applications of Artificial Intelligence,2003,(16):657-665.
54.黄景涛,马龙华,钱积新.一种用于多分类问题的改进支持向量机[J],浙江大学学报(工学版),2004,38(12):1633-1636.
55.余艳芳,高大启.一种改进的最小二乘支持向量机及其应用[J],计算机工程与科学,2006,28(2):69-71.
56.C Cortes,V Vapnik.Support vector networks[J].Machine Learning,1995,20:273-297.
57.S Jacoub,Y Abdeljaoued,E Mayoraz.Fusion of face and speech data for person identity verification[J].IEEETrans on Neural Network,1999,10(5):1065-1074.
58.Shimshoni Y,Intrator N.Classification of Seismic Signals by Integrating Ensembles of Neural Networks.IEEE Transactions on Signal Processing,1998,46(5):1194-1201.
59.Kim K,Kim C.Forecasting Time Series with Genetic Fuzzy Prodictor Ensemble.IEEE Transactions on Fuzzy Systems,1997,5(4):523-535.
60.Russo A P.Constrained Neural Networks for Recognition of Passive Sonar Signals Using Shape.In:Proceedings of the IEEE Conference on Neural Networks for Ocean Engineering,1991,69-76.
61.Stamatatos E and Widmer G Automatic identification of music performers with learning ensembles[J].Artificial Intelligence,2005,(165):37-56.
62.Kim E,Kim W and Lee Y.Combination of multiple classifiers for the customer's purchase behavior prediction.Decision Support Systems,2003,34:167-175.
63.Shin H.W.and Sohn S.Y.Combining both ensemble and dynamic classifier selection schemes for prediction of mobile internet subscribers[J].Expert Systems with Application,2003,(25):63-68.
64.He C,Girolami M and Ross G.Employing optimized combinations of one-class classifiers for automated currency validation.Pattern Recognition,2004(37):1085-1096.
65.Yu K,Jiang X and Bunke H.Lipreading:A classifier combination approach.Pattern Recogition Letters[J],1997,18(1.1):1421-1426.
66.路志英,赵智超,郝为.基于人工神经网络的多模型综合预报方法[J],计算机应用,2004,24,(4):50-52.
67.刘伟嵬,颜云辉,孙宏伟.一种基于邻域噪声评价法的图像去噪算法[J],东北大学学报,2008,29(7):1033-1036.
68.王永慧,颜云辉,梁惠升.带钢表面缺陷图像小波融合方法[J],东北大学学报,2009,30(5):733-737.
69.E.Mjolsness and D.DeCoste.Machine Learning for Science:State of the Art and Future Prospects.Science[J].2001,(293):2051-2055.
70.B.Scholkopf,A.Smola.Nonlinear component analysis as kernel eigenvalue problem,Neural Computation[J],1998,10(5):1299-1319.
71.王旭,王宏,王文辉.人工神经元网络原理与应用[M],沈阳:东北大学出版社, 2000.
72. Shin H.W. and Sohn S.Y. Combining both ensemble and dynamic classifier selection schemes for prediction of mobile internet subscribers[J]. Expert Systems with Application,2003, (25):63-68.
73. T. Kohonen, K. Torkkola, M. Shozakai, J. Kangas, O.Venta, Microprocessor implementation of a large vocabularyspeech recognizer and phonetic typewriter for Finnishand Japanese, Proceedings of the European Conference ofSpeech Technology, Edinburgh, 1987, 2377-2380.
74. T. Kohonen, Self-organizing maps of symbol strings[J], Neurocomputing, ELSEVIER, 1998, 19-30.
75. D.H. Graf, W.R. Lalonde, Neuroplanners for hand/eye coordination, Proceedings of the International Joint Conference on Neural Networks, Washington, 1989, 543 -548.
76. I.K. Sethi , I. Coman. Image retrieval using hierarchical self-organizing feature maps[J], Pattern Recognition Letters, Elsevier Science Inc, New York, 1999, pp. 1337-1345.
77. Z.li -Zhang, S.Sheng-he, Z. Fu-chun, etc. Image fusion based on median filters and SOFM neural networks: a three-step scheme, Signal Processing, EURASIP, 2001, 1325-1330.
78. X.Jian-qiao, L.bin Z.Yong-heng. Automatic classification of stellar spectra using the SOFM method[J], Chinese Astronomy and Astrophysics, Beijing, 2001, 120-131.
79. F. Sebelius, L. Eriksson, H. Holmberg, A. Levinsson, etc. Classification of motor commands using a modified self-organising feature map [J], Medical Engineering & Physics, IPEM, 2005, 403-413.
80. A. Laha, R. Nikhil Pal. Dynamic generation of prototypes with self-organizing feature maps for classifier design [J], Pattern Recognition, ELSEVIER, 2001, 315-321.
81. Jang Hee Lee, Sung Jin You, Sang Chan Park. A new intelligent SOFM-based sampling planfor advanced process control[J], Expert Systems with Applications, ELSEVIER, 2001, 133-151.
82. S. Patra, S. Ghosh, A. Ghosh. Unsupervised change detection in remote-sensing images using modified self-organizing feature map neural network. International Conference on Computing:Theory and Applications(ICCTA-2007),Kolkata,India,2007,716-720.
83.L.Bruzzone,D.F.Prieto.Automatic analysis of the difference image for unsupervised change detection.IEEE,2000,1171-1182.
84.T.Kohonen.Self-organized formation of topologically correct feature maps[J],Biological Cybernetics,Springer Berlin/Heidelberg,1982,59-69.
85.T.Kohonen.Fast Evolutionary Learning with Batch-Type Self-Organizing Maps[J],Neural Processing Letters,1999,153-162.
86.T.Kohonen.How to make large self-organizing maps for nonvectorial data[J],Neural Networks,2002,945-952.
87.T.Kohonen.Visual Feature Analysis by the Self-Organising Maps[J],Neural Comput & Applications,Springer-Verlag London,1998,273-286.
88.魏天宇.板带材表面缺陷组合特征的降维聚类识别算法研究[D].沈阳:东北大学,2006:21-29.
89.李骏,颜云辉,王成明等.板带材缺陷检测中的多特征优化组合方法研究[J],计算机工程与应用,2007,43(22):197-200.
90.Aitkenhead M J.A co-evolving decision tree classification method[J].Expert Systems with Applications,2008(34):18-25.
91.Arivazhagan S,Ganesan L.Texture classification using wavelet transform[J].Pattern Recognition Letters,2003(24):1513-1521.
92.Kohonen T.How to make large self-organizing maps for nonvectorial data[J].Neural Networks,2002:945-952.
93.Kohonen T.Visual Feature Analysis by the Self-Organising Maps[J].Neural Comput & Applications,1998:273-286.
94.M.Jayabharata Reddy,D.K.Mohanta.A wavelet-fuzzy combined approach for classification and location of transmission line faults[J],Electrical Power and Energy Systems,2007,29:669-678.
95.M.J.Aitkenhead.A co-evolving decision tree classification method[J],Expert Systems with Applications,2008,34:18-25.
96.Arivazhagan S,Ganesan L.Texture classification using wavelet transform[J],Pattern Recognition Letters, 2003, 24:1513-1521.
97. I.B.Gurevivh. Comparative analysis and classification of features for image models[J], Pattern Recognition and Image Analysis, 2006,16(3):265-297.
98. Joon Hur, Jong Woo Kim. A hybrid classification method using error pattern modeling[J],Expert Systems with Applications, 2008,34 : 231-241.
99. Jie Li, Xianglong Tang. A new classification model with simple decision rule for discovering optimal feature gene pairs [J], Computers in Biology and Medicine, 2007,37:1637-1646.
100. J.L. Giraudel and S. Lek. A Comparison of self-organizing map algorithm and some conventional statistical methods for ecological community ordination[J], Ecological Modelling, 2001, 146:329-339.