A connectionist approach for gray level image segmentation

A connectionist network is presented for segmenting gray level images. The network detects the local peaks in the inverted histogram which will correspond to the bottoms of the valleys in the actual histogram. The neural network implementation successfully uses circumstantial evidence and detects multiple winners over the entire range of gray values such that these winners correspond to multiple thresholds for segmenting the image. The dynamics of the network has been analyzed and the conditions for convergence have been established. Experimental results obtained by applying the network for segmenting two X-ray images are presented.<<ETX>>

[1]  José Manuel Rebordão,et al.  An amplitude segmentation method based on the distribution function of an image , 1984, Comput. Vis. Graph. Image Process..

[2]  R. Kohler.  A segmentation system based on thresholding , 1981 .

[3]  Robert M. Haralick,et al.  Automatic multithreshold selection , 1984, Comput. Vis. Graph. Image Process..

[4]  Santanu Chaudhury,et al.  A connectionist approach for peak detection in Hough space , 1992, Pattern Recognit..

[5]  William J. Wolfe,et al.  K-winner networks , 1991, IEEE Trans. Neural Networks.

[6]  P.K Sahoo,et al.  A survey of thresholding techniques , 1988, Comput. Vis. Graph. Image Process..

[7]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.