Title :
Real-life application case studies using CMOS 0.8 μm CNN universal chip: analogic algorithm for motion detection and texture segmentation
Author :
Földesy, Péter ; Zarándy, Ákos ; Szolgay, Péter ; Szirányi, Tamás
Author_Institution :
Comput. & Autom. Inst., Hungarian Acad. of Sci., Budapest, Hungary
Abstract :
Using a 20×22 CNN Universal Machine chip two application case studies are presented. A new analogic CNN algorithm is shown to detect objects having larger size than a given value on black-and-white image sequences moving in a given range of direction and speed (17 μs processing speed could be achieved). An extremely fast texture classification analogic algorithm is given next with approximately 2 μs processing speed and with less than 5% misclassification error rate for 4 natural textures in a real-life testing environment
Keywords :
CMOS analogue integrated circuits; cellular neural nets; image classification; image segmentation; image sequences; image texture; motion estimation; neural chips; object detection; 0.8 micron; 17 mus; 20×22 CNN Universal Machine chip; CMOS 0.8 μm CNN Universal chip; analogic algorithm; black-and-white image sequences; misclassification error rate; motion detection; natural textures; texture classification; texture segmentation; Cellular neural networks; Computer aided software engineering; Logic; Motion detection; Prototypes; Registers; Switches; Testing; Thyristors; Turing machines;
Conference_Titel :
Cellular Neural Networks and their Applications, 1996. CNNA-96. Proceedings., 1996 Fourth IEEE International Workshop on
Conference_Location :
Seville
Print_ISBN :
0-7803-3261-X
DOI :
10.1109/CNNA.1996.566601
