基于RBFNN模糊融合的纸病在线辨识

周强; 杨雁南; 刘勇; 汤伟

doi:doi:10.3788/gzxb20134208.1002

光子学报, 2013, 42 (8): 1002, 网络出版: 2013-09-25

基于RBFNN模糊融合的纸病在线辨识

Online Paper Defect Identification Based on Fuzzy Fusion of RBFNN

论文大纲

周强 ^*杨雁南刘勇汤伟

作者单位

陕西科技大学电气与信息工程学院,西安 710021

摘要

针对当前的各种纸病辨识方法只能对于一种或有限几种纸病有效辨识，且不能准确辨识难点纸病的问题，在全面分析纸病特征、研究和归纳各类纸病辨识方法的基础上，本文提出使用模糊融合器对纸病图像的多种特征值进行特征层融合，把多个纸病辨识方法结合在一起，以达到纸病高效、全面辨识的目的.由于径向基神经网络结构与模糊推理结构的等价性，使得径向基神经网络实现的多种纸病特征的信息融合系统具有结构简单和快速性的特点.实验表明：本文方法可以准确识别包括难点纸病在内的各种主要纸病.

Abstract

Current paper defects identification methods has two radical problems. First, every current method can only identify one or few defects. Second, current methods can hardly detect the complex paper defects accurately. In view of these problems, based on comprehensive analysis of paper defect features, research and summary of all kinds of paper defect identification methods, Fuzzy fusion device is used to conduct feature layer fusion with some paper defect characteristic values, and combine multiple paper defect identification methods, aiming to achieve more efficient and comprehensive paper defect identification. According to the construction equivalence between RBF Neural Network and fuzzy reasoning, the paper defect features information fusion system on basis of RBFNN has the advantage of simple structure and rapidity. Experiments have shown that the method presented is practicable to identify the primary paper defects accurately, including complex paper defects.

参考文献

[1] 杨波,周强,张刚强.基于几何及灰度特征的纸病检测算法研究［J］.中国造纸,2011,30(9):52-53.

YANG Bo, ZHOU Qiang, ZHANG Gangqiang. Study on algorithm of paper defect detection based on geometric and gray feature［J］. China Pulp & Paper, 2011, 30(9): 52-53.

[2] 徐志鹏,须文波.基于小波奇异性的纸病检测［J］.中国造纸学报,2004,19(2):146-151.

XU Zhipeng, XU Wenbo. Paper defects detection based on singular characterization［J］. Transactions of China Pulp and Paper, 2004, 19(2): 146-151.

[3] 张刚强,周强. 改进Hough变换在纸病检测系统中的应用［J］.中国造纸学报,2011,26(4):38-40.

ZHANG Gangqiang, ZHOU Qiang. Application of improved hough transform in web inspection system［J］. Transactions of China Pulp and Paper, 2011, 26(4): 38-40.

[4] ANZAR Alam, JAN Thim, MATTIAS O'Nils, et al. Online surface characterization of paper and paperboards in a widerang of the spatial wavelength spectrum［J］. Applied Surface Science, 2012, 136(4): 7928-7934.

[5] MONICA Benito, DANIEL Pena.Detecting defects with image data［J］. Computational Statistics & Data Analysis, 2007, 51: 6395-6402.

[6] SHANMUGAVADIVU P, SIVAKUMAR V. Fractal dimension based texture analysis of digital images［J］. Procedia Engineering, 2012, 38: 2981-2985.

[7] ODEMIR Martinez Bruno, RODRIGO de Oliveira Plotze, MAURICIO Falvo, et al. Fractal dimension applied to plant identification［J］. Information Sciences, 2008, 178(12): 2722-2731.

[8] 殷燕萍,熊智新,胡慕伊. 基于阈值分割及分形特征的纸病图像识别算法研究［J］.中国造纸学报,2011,26(4):41-44.

YIN Yanping, XIONG Zhixin, HU Muyi. Identification algorithm of paper defects based on threshold segmentation and fractal characteristics［J］. Transactions of China Pulp and Paper, 2011, 26(4): 41-44.

[9] WING W Y Ng, ANDRES Dorado, DANIEL S, et al. Image classification with the use of radial basis function neural networks and the minimization of the localized generalization error［J］. Pattern Recognition, 2007, 40(1): 19-25.

[10] 靖固,刘璐杨,于晓洋.基于FPGA多变量模糊神经网络控制器设计［J］.哈尔滨理工大学学报,2011,16(2):45.

JING Gu, LIU Luyang, YU Xiaoyang. The research of multivariable fuzzy neural network controller based on FPGA［J］. Journal of Harbin University of Science and Technology, 2011, 16(2): 45.

[11] KUMANAN S, JESUTHANAM C P, KUMAR R A. Application of multiple regression and adaptive neuro fuzzy inference system for the prediction of surface roughness［J］. Advanced Manufacturing Technology, 2008, 35(7-8): 781-785.

[12] 刘煜,李言俊,张科.一种多像素图像边缘提取方法［J］.光子学报,2007,36(2):380-382.

LIU Yu, LI Yanjun, ZHANG Ke. A method of multipixels edge detecting of image［J］. Acta Photonica Sinica, 2007, 36(2): 380-382.

[13] 李俊山,马颖,赵方舟,等.改进的canny图像边缘检测算法［J］.光子学报,2011,40(1):51-53.

LI Junshan, MA Ying, ZHAO Fangzhou, et al. A novel arithmetic of image edge detection of canny operator［J］. Acta Photonica Sinica, 2011, 40(1): 51-53.

[14] 路雅宁,郭雷,李晖晖.结合边缘信息和图像特征信息的曲波域遥感图像融合［J］.光子学报,2012,41(9):1121-1122.

LU Yaning, GUO Lei, LI Huihui. Remote sensing image fusion using edge information and features of SAR image based on curvelet transform［J］. Acta Photonica Sinica, 2012, 41(9): 1121-1122.

[15] 孙显,王宏琦,张道兵,等.基于多特征融合的城市遥感图像自动解译方法［J］.光子学报,2010,39(1):179-181.

SUN Xian, WANG Hongqi, ZHANG Daobing, et al. An automatic interpretation approach for urban remote sensing image based on multiple features integration［J］. Acta Photonica Sinica, 2010, 39(1): 179-181.

周强, 杨雁南, 刘勇, 汤伟. 基于RBFNN模糊融合的纸病在线辨识[J]. 光子学报, 2013, 42(8): 1002. ZHOU Qiang, YANG Yannan, LIU Yong, TANG Wei. Online Paper Defect Identification Based on Fuzzy Fusion of RBFNN[J]. ACTA PHOTONICA SINICA, 2013, 42(8): 1002.

基于RBFNN模糊融合的纸病在线辨识

关于本站 Cookie 的使用提示

全站搜索

基于RBFNN模糊融合的纸病在线辨识

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索