Title :
The continuous retina: image processing with a single-sensor artificial neural field network
Author :
Mills, Jonathan W.
Author_Institution :
Dept. of Comput. Sci., Indiana Univ., Bloomington, IN, USA
Abstract :
Silicon retinas are typically implemented with multiple photosensors. Recent work with VLSI extended analog computers has led to a single-photosensor retina. An image focused on it generates a current gradient within the sensor that is discretized into an analog output vector, then classified by an artificial neural field network. A VLSI implementation recognizes several letters and fits on one MOSIS “TinyChip”
Keywords :
MOS integrated circuits; VLSI; image processing equipment; image sensors; neural chips; semiconductor devices; MOSIS TinyChip; VLSI extended analog computers; VLSI implementation; analog output vector; continuous retina; current gradient; image processing; silicon retinas; single-photosensor retina; single-sensor artificial neural field network; Analog computers; Biological system modeling; Biosensors; Brain modeling; Image processing; Image sensors; Retina; Sensor arrays; Silicon; Very large scale integration;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549014
