Title :
Hysteresis quantizer
Author :
Jin´no, Kenya ; Tanaka, Manioru
Author_Institution :
Sophia Univ., Tokyo, Japan
Abstract :
This paper proposes two type quantizers by using mutual connected neural networks. Since each cell of the neural networks has hysteresis properties, these quantizers can convert any input signals into a suitable quantization output. Also, we propose its application for image processing which can be intensity conversion. By using an area intensity method, we can get high quality output images in spite of to use bilevel output function
Keywords :
hysteresis; image processing; neural nets; quantisation (signal); hysteresis quantizer; image processing; intensity conversion; mutual connected neural networks; Differential equations; Hysteresis; Image converters; Image processing; Neurofeedback; Neurons; Output feedback; Quantization; State feedback;
Conference_Titel :
Circuits and Systems, 1997. ISCAS '97., Proceedings of 1997 IEEE International Symposium on
Print_ISBN :
0-7803-3583-X
DOI :
10.1109/ISCAS.1997.608919