Boundary identification for wood defects using Neural Network based on Matlab programming

Here we present a novel method to detect the boundaries of wood defects in X-ray wood images using the Hopfield Neural Network (HNN) algorithm based on Matlab programming. An improved energy function was designed for the HNN to perform the boundary detection which was formulated, in this paper, as an optimization process that could locate the boundary points of wood defects. The gray value of each pixel in the image was considered as a neuron state of HNN. An initial defect boundary was roughly estimated using Canny Algorithm. Based on the initial states, all the neuron's states updated till the energy function get the minimum value. The defect boundary was identified when the neurons get the final states. The results show we obtain a more accurate boundary using this method comparing to using other traditional methods, and the noises were effectively removed. In this paper, we also find a way to do the boundary detection based on Matlab programming.

[1]  Chuan-Yu Chang,et al.  A contextual-based Hopfield neural network for medical image edge detection , 2004, 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763).

[2]  Noel D.G. White,et al.  Assessment of soft X-ray imaging for detection of fungal infection in wheat , 2009 .

[3]  Chuan-Yu Chang.  A contextual-based Hopfield neural network for medical image edge detection , 2004 .

[4]  Hong Yan,et al.  Computerized tumour boundary detection using a Hopfield neural network , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[5]  Zhong Yang,et al.  A method based on rank-ordered filter to detect edges in cellular image , 2009, Pattern Recognit. Lett..

[6]  Gonzalo Pajares,et al.  A Hopfield Neural Network for combining classifiers applied to textured images , 2010, Neural Networks.

[7]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[8]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[9]  Witold Pedrycz,et al.  Dynamic edge tracing: Boundary identification in medical images , 2009, Comput. Vis. Image Underst..

[10]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[11]  Jun Shen,et al.  Neuro-fuzzy synergism to the intelligent system for edge detection and enhancement , 2003, Pattern Recognit..

[12]  Yan Zhu,et al.  Computerized tumor boundary detection using a Hopfield neural network , 1997, IEEE Transactions on Medical Imaging.

[13]  Chien-Chang Chen,et al.  Edge detection improvement by ant colony optimization , 2008, Pattern Recognit. Lett..