Wood defects classification using laws texture energy measures and supervised learning approach

Abstract Machine vision based inspection systems are in great focus nowadays for quality control applications. The proposed work presents a novel approach for classification of wood knot defects for an automated inspection. The proposed technique utilizes gray level co-occurrence matrix and laws texture energy measures as texture feature extractors and feed-forward back-propagation neural network as classifier. The proposed work involves the comparison of gray level co-occurrence matrix based features with laws texture energy measures based features. Firstly it takes contrast, correlation, energy and homogeneity as input parameters to a feed-forward back propagation neural network to predict wood defects and then it take energy calculated from laws texture energy measures based energy maps as input feature to a feed-forward back propagation neural network. Mean Square Error (MSE) for training data is found to be 0.0718 and 90.5% overall average classification accuracy is achieved when laws texture energy measures based features are used as input to the neural network as compared to gray level co-occurrence matrix based input features where MSE for training data is found to be 0.10728 and 84.3% overall average classification accuracy is achieved. The proposed technique shows promising results to classify wood defects using a feed forward back-propagation neural network.

[1]  A. Nikita,et al.  Evaluation of Texture Features in Hepatic Tissue Characterization from Non-enhanced CT Images , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[2]  Li Li,et al.  Pattern recognition and size determination of internal wood defects based on wavelet neural networks , 2009 .

[3]  Hongbo Mu,et al.  Pattern Recognition of Wood Defects Types Based on Hu Invariant Moments , 2009, 2009 2nd International Congress on Image and Signal Processing.

[4]  J. Dheeba,et al.  Computer-aided detection of breast cancer on mammograms: A swarm intelligence optimized wavelet neural network approach , 2014, J. Biomed. Informatics.

[5]  Gang Yu,et al.  A cluster-based wavelet feature extraction method and its application , 2010, Eng. Appl. Artif. Intell..

[6]  Yung-Chang Chen,et al.  Texture features for classification of ultrasonic liver images , 1992, IEEE Trans. Medical Imaging.

[7]  C. L. Todoroki,et al.  Automated knot detection with visual post-processing of Douglas-fir veneer images , 2010 .

[8]  Charles C. Brunner,et al.  Image segmentation algorithms applied to wood defect detection , 2003 .

[9]  S. Radovan,et al.  An approach for automated inspection of wood boards , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[10]  Hui Wang,et al.  Research on recognition of wood texture based on integrated neural network classifier , 2010, 2010 International Conference on Intelligent Control and Information Processing.

[11]  J. Correa,et al.  Knots detection in wood using microwaves , 2005, Wood Science and Technology.

[12]  C. Chappard,et al.  Laws’ masks descriptors applied to bone texture analysis: an innovative and discriminant tool in osteoporosis , 2008, Skeletal Radiology.

[13]  Duc Truong Pham,et al.  Neural network design and feature selection using principal component analysis and Taguchi method for identifying wood veneer defects , 2014 .

[14]  Antti J. Koivo,et al.  Hierarchical classification of surface defects on dusty wood boards , 1994, Pattern Recognit. Lett..

[15]  Adilson Gonzaga,et al.  Wood texture classification by fuzzy neural networks , 1999, Electronic Imaging.

[16]  Ning Ye,et al.  Locating theWood Defects with Typical Features and SVM , 2008 .

[17]  Hannu Kauppinen,et al.  COLOR AND TEXTURE BASED WOOD INSPECTION WITH NON-SUPERVISED CLUSTERING , 2001 .

[18]  Pablo A. Estévez,et al.  Automated visual inspection system for wood defect classification using computational intelligence techniques , 2009, Int. J. Syst. Sci..

[19]  Isabelle Debled-Rennesson,et al.  Automatic knot detection and measurements from X-ray CT images of wood: A review and validation of an improved algorithm on softwood samples , 2012 .

[20]  Richard W. Conners,et al.  Identifying and Locating Surface Defects in Wood: Part of an Automated Lumber Processing System , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Mahrokh G. Shayesteh,et al.  Classification of wood surface defects with hybrid usage of statistical and textural features , 2012, 2012 35th International Conference on Telecommunications and Signal Processing (TSP).

[22]  A.L. Koerich,et al.  Wood Defect Detection using Grayscale Images and an Optimized Feature Set , 2006, IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics.

[23]  Chao Li,et al.  Using computer vision and compressed sensing for wood plate surface detection , 2015 .

[24]  Olli Silvén,et al.  Wood Inspection With Non-Supervised Clustering , 2000 .

[25]  Khurram Kamal,et al.  Wood defects classification using GLCM based features and PSO trained neural network , 2016, 2016 22nd International Conference on Automation and Computing (ICAC).

[26]  Olli Silven,et al.  Nonsegmenting defect detection and SOM-based classification for surface inspection using color vision , 1999, Industrial Lasers and Inspection.

[27]  Yudy Purnama,et al.  Mammogram Classification using Law's Texture Energy Measure and Neural Networks , 2015 .

[28]  Hafiz Adnan Habib,et al.  Modified Laws Energy Descriptor for Inspection of Ceramic Tiles , 2004 .

[29]  Xie Yong-hua,et al.  Study on the identification of the wood surface defects based on texture features , 2015 .

[30]  Erol Sarigul,et al.  Rule-driven defect detection in CT images of hardwood logs , 2003 .