Improved Tropical Wood Species Recognition System based on Multi-feature Extractor and Classifier

An automated wood recognition system is designed to classify tropical wood species.The wood features are extracted based on two feature extractors: Basic Grey Level Aura Matrix (BGLAM) technique and statistical properties of pores distribution (SPPD) technique. Due to the nonlinearity of the tropical wood species separation boundaries, a pre classification stage is proposed which consists ofKmeans clusteringand kernel discriminant analysis (KDA). Finally, Linear Discriminant Analysis (LDA) classifier and KNearest Neighbour (KNN) are implemented for comparison purposes. The study involves comparison of the system with and without pre classification using KNN classifier and LDA classifier.The results show that the inclusion of the pre classification stage has improved the accuracy of both the LDA and KNN classifiers by more than 12%.

Authors:

• Marzuki Khalid
• RubiyahYusof
• AnisSalwaMohdKhairuddin

Keywords:

• Tropical wood species
• nonlinear data
• featureextractors
• classification

References:

[1] State of the World's Forests, FAO, 1995-2010
[2] M. Khalid, Lew Y. L., R. Yusof and M. Nadaraj, "Design of An
Intelligent Wood Species Recognition System,"IJSSST, Vol. 9, No. 3,
September 2008
[3] R. Yusof, Nenny R. Rosli, M. Khalid,"Using Gabor Filters as Image
Multiplier for Tropical Wood Species Recognition System,"12th
International Conference on Computer Modelling and Simulation, 2010,
pp.289-294.
[4] Keqi Wang and XuebingBai, "Research on classification of wood
surface texture based on feature level data fusion,"2nd International
Conference on Industrial Electronics and Applications, 2007
[5] UswahKhairuddin, RubiyahYusof, Marzuki Khalid and Florian
Cordova, "Optimized Feature Selection for Improved Tropical Wood
Species Recognition System,"ICIC Express letters, Part B:
Applications, An International Journal of Research and Surveys,
Volume 2, Number 2, April 2011, pp 441-446.
[6] Xuejie Qin; Yee-Hong Yang,"Similarity measure and learning with gray
level aura matrices (GLAM)for texture image retrieval"Proceedings of
the 2004 IEEE Computer Society Conference on Computer Vision and
Pattern Recognition CVPR, 2004. Vol. 1, pp. 326 - I-333
[7] Park, C.H. and Park, H,"Nonlinear discriminant analysis using kernel
functions and the generalized singular value decomposition,"SIAM
Journal on Matrix Analysis and Applications, 2005
[8] Howland,P and Park, H. "Generalizing Discriminant Analysis Using the
Generalized Singular Value Decomposition,"IEEE Transaction, PAM,
2004
[9] Shi Na; Liu Xumin; Guan Yong,"Research on k-means Clustering
Algorithm: An Improved k-means Clustering Algorith,"3rd
International Conference on Intelligent Information Technology and
Security Informatics (IITSI), 2010, pp.63-67,
[10] Ming-Hseng Tseng, Chang-Yun Chiang, Ping-Hung Tang, Hui-Ching
Wu, "A study on cluster validity using intelligent evolutionary k-means
approach", Proceedings of the ninth international conference on
machine learning and cybernatics, July 2010.
[11] Zhu XiaoKai and Li Xiang, "Image kernel for recognition,"Proceedings
ICSP2008, 2008.
[12] Fei Ye, Zhiping Shi and Zhongzhi Shi, "A comparative study of PCA,
LDA and Kernel LDA for image classification",International
Symposium on ubiquitous virtual reality, 2009.
[13] Wen-Sheng Chen, Pong C Yuen, and Zhen Ji, "Kernel subspace LDA
with convolution kernel function for face recognition,"International
Conference on Wavelet Analysis and Pattern Recognition, 2010.
[14] Yunfei Jiang, Xinyu Chen, Ping Guo and Hanqing Lu, "An improved
random sampling LDA for face recognition,"Congress on Image and
Signal Processing, 2008.
[15] Jin HuaXu, Hong Liu, "Web user clustering analysis based on k-means
algorithm,"International conference in information, networking and
automation (ICINA), 2010.