Please wait a minute...
浙江大学学报(工学版)
J4  2011, Vol. 45 Issue (12): 2120-2126    DOI: 10.3785/j.issn.1008-973X.2011.12.009
    
Gabor filter and latent semantic analysi based
burning state recognition
LI Wei-tao, ZHOU Xiao-jie, CHAI Tian-you
State Key Laboratory of Integrated Automation for Process Industry,Research Center for Automation,
Northeastern University, Shenyang 110004, China
Download:   PDF(0KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

A new method based on Gabor filter pre-processing and latent semantic analysis (LSA) was proposed to achieve accurate burning state recognition for the flame image of rotary kiln burning zone, with the goal of avoiding inaccurate feature extraction and poor burning state recognition result involved by the image segmentation-based methods. As the pre-processing step, the designed compact Gabor filter bank was employed to distinguish region of interests with distinguishable texture properties to facilitate the subsequent feature extraction and burning state recognition step. For the filtered flame images, the improved LSA method was employed to extract feature vectors to recognize the burning state, with the goal of reducing the dimensionality of features and avoiding zero-frequency problem. Experimental results showed the feasibility of this flame image-based method to extract feature directly to recognize the burning state. Moreover, the recognition performance was superior to the without Gabor filter-based method, traditional LSAbased method, temperaturebased method, and image segmentation-based methods.

Published: 01 December 2011
CLC:  TP 274  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

LI Wei-tao, ZHOU Xiao-jie, CHAI Tian-you. Gabor filter and latent semantic analysi based
burning state recognition. J4, 2011, 45(12): 2120-2126.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2011.12.009     OR     https://www.zjujournals.com/eng/Y2011/V45/I12/2120


基于Gabor滤波器和潜在语义分析的烧成状态识别

采用Gabor滤波器预处理与潜在语义分析相结合的方法,对回转窑烧成带火焰图像的烧成状态进行了更为准确的识别,避免了基于图像分割技术带来的不精确特征提取和较差的识别结果.基于所构建的压缩Gabor滤波器组对火焰图像进行预处理,增强具有不同纹理特性的特征区域的可分性以有利于后续的特征提取和状态识别步骤.对预处理后的火焰图像采用改进的潜在语义分析提取特征向量进行状态识别,以降低特征维数并避免零频问题.实验结果表明：直接从火焰图像中提取特征进行状态识别的方法是可行的,并且识别的效果较未采用Gabor滤波器预处理、传统潜在语义分析、烧成带温度和图像分割等方法的效果更优.

［1］ RUBY C W. A new approach to expert kiln control ［C］ ∥ Proc of IEEE Cement Industry Technical. Hershey, USA: IEEE, 1997: 339-412.
［2］ AKALP M, DOMINGUEZ A L, LONGCHAMP R. Supervisory fuzzy control of a rotary cement kiln ［C］ ∥ Proc of IEEE Electrotechnical Conference. Antalya, Turkey: IEEE, 1994: 754-757.
［3］ JARVENSIVU M, SAARI K, JAMSAJOUNELA S L. Intelligent Control System of an Industrial Lime Kiln Process ［J］. Control Engineering Practice, 2001, 9(6): 589-606.
［4］ 李树涛, 王耀南. 基于神经网络的回转窑火焰图像分割 ［J］. 仪器仪表学报, 2001,22(1): 10-14.
LI Shutao, WANG Yaonan. Segmentation of kiln flame image based on neural networks ［J］. Chinese Journal of Scientific Instrument, 2001, 22(1): 10-14.
［5］ SUN P, CHAI T Y, ZHOU X J. Rotary kiln flame image segmentation based on FCM and Gabor wavelet based texture coarseness ［C］ ∥ Proc of World Congress on Intelligent Control and Automation. Chongqing, China: IEEE, 2008: 7615-7620.
［6］ 姜慧研, 崔晓亮, 周晓杰, 等. 基于改进的双快速行进法的图像分割方法 ［J］. 仪器仪表学报, 2008, 20(3): 803-810.
JIANG Huiyan, CUI Xiaoliang, ZHOU Xiaojie, et al. Image segmentation based on improved dual fast marching method ［J］. Journal of System Simulation, 2008, 20(3): 803-810.
［7］ IDRISSA M, ACHEROY M. Texture classification using Gabor filters ［J］. Pattern Recognition Letters, 2002, 23(9): 1095-1102.
［8］ LOWE D G. Distinctive image features from scaleinvariant keypoints ［J］. International Journal of Computer Vision, 2004, 60(2): 91-110.
［9］ SIVIC J, ZISSERMAN A. Video Google: A Text retrieval approach to object matching in videos ［C］ ∥ IEEE International Conference on Computer Vision. Nice, France: IEEE, 2003: 1470-1477.
［10］ YATES R B, NETO B R. Modern Information Retrieval ［M］. New York: ACM Press, 1999.
［11］ DEERWESTER S C, DUMAIS S T, LANDAUER T K, et al. Indexing by latent semantic analysis ［J］. Journal of the American Society of Information Science, 1990, 41(6): 391-407.
［12］ WITTEN I H, BELL T C. The zerofrequency problem: estimating the probabilities of novel events in adaptive text compression ［J］. IEEE Trans on Information Theory, 1991, 37(4): 1085-1094.
［13］ 杨重愚. 氧化铝生产工艺学 ［M］. 北京: 冶金工业出版社, 1993.

［14］ ZHOU X J, CHAI T Y. Patternbased hybrid intelligent control for rotary kiln process ［C］ ∥ International Conference on Control Applications. Singapore: IEEE, 2007: 31-35.
［15］ LI S, TAYLOR J S. Comparison and fusion of multiresolution features for texture classification ［J］. Pattern Recognition Letters, 2004, 26(5): 633-638.
［16］ CLAUSI D A, DENG H. Designbased texture feature fusion using Gabor filters and cooccurrence probabilities ［J］. IEEE Trans. Image Process, 2005, 14(7): 925-936.
［17］ JAIN A K, DUIN R P W, MAO J C. Statistical Pattern Recognition: A Review ［J］. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(1): 4-37.
［18］ BIANCONI F, FERMANDEZ A. Evaluation of the effect of Gabor filter parameters on texture classification ［J］. Pattern Recognition, 2007, 40(12): 3325-3335.
［19］ LI W T, MAO K Z, ZHANG H, et al. Designing compact Gabor filter banks for efficient texture feature extraction ［C］ ∥ International Conference on Control, Automation, Robotics and Vision. Singapore: IEEE, 2010: 1193-1198.
［20］ SPECHT D F. Probabilistic neural network ［J］. Neural Network, 1990, 3(1): 109-118.
［21］ CHEMICK M R. Bootstrap methods: A practitioner’s guide ［M］. New York: Wiley, 1999.
［22］ YAN F X, ZHANG H, KUBE C R. A multistage adaptive thresholding method ［J］. Pattern Recognition Letters, 2005, 26(8): 1183-1191.
[1] LIU Li-jun, DAI Hong-bin, ZHU Rong-hua. Residual stress of laser welding joint of stainless steel automobile vent pipeL[J]. J4, 2011, 45(1): 136-140.