Title :
An image binarization system for composite pictures
Author :
Chigusa, Yasutami ; Hattori, Taizo ; Ikegami, Munemitsu ; Tanaka, Mamoru
Author_Institution :
Fac. of Eng., Tokyo Eng. Univ., Japan
Abstract :
The authors describe a novel binarization method based on neural dynamics for mixed gray-level and binary pictures. The Hopfield neural network is applied to this system. The threshold of each neuron is adaptively decided to be proportional to the gray-level of the corresponding input pixel, then the steady state of the network is assumed as the output image. The proposed algorithm is massively parallel. The two main advantages of this dynamic system are clearly established. One is that this system transforms composite pictures to pseudo gray-level pictures, without any segmentation. The other is that blurred images, especially in binary pictures, are reconstructed as sharpened pseudo gray-level pictures. The binarization method proposed is evaluated by using data obtained from real images and from the binary images reconstructed by the conventional binarization method
Keywords :
Hopfield neural nets; image processing; parallel algorithms; parallel architectures; pipeline processing; Hopfield neural network; binary pictures; blurred images; composite pictures; image binarization system; massively parallel algorithm; mixed gray-level/binary pictures; neural dynamics; pseudo gray-level pictures; Hardware; Hopfield neural networks; Image reconstruction; Image segmentation; Neural networks; Neurons; Retina; Silicon; Sparse matrices; Steady-state;
Conference_Titel :
Circuits and Systems, 1992. ISCAS '92. Proceedings., 1992 IEEE International Symposium on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-0593-0
DOI :
10.1109/ISCAS.1992.230501