Title :
Subthreshold implementation of a 2D CNN Gabor-type focal plane filter
Author_Institution :
Dept. Electr. & Electron. Eng., Hong Kong Univ. of Sci & Technol., Kowloon
Abstract :
We describe the implementation of a focal plane CNN array for computing the outputs of orientation selective filters similar to Gabor filters using weak inversion transistor circuits. Both the scale and the orientation selectivity of the filter can be tuned electronically. We exploit the concept of the transistor as a pseudo-conductance or diffuser and use current, rather than voltage to represent signals of interest. This design enables energy efficient computation of the filter responses. Test results from a 12×14 pixel array fabricated in 1.2 μm technology are presented
Keywords :
cellular neural nets; computational complexity; image processing; transistor circuits; 1.2 mum; 12 pixel; 14 pixel; 168 pixel; 2D CNN Gabor-type focal plane filter; diffuser; energy efficient computation; focal plane CNN array; orientation selective filters; orientation selectivity; pseudo-conductance; scale selectivity; subthreshold implementation; transistor; weak inversion transistor circuits; Band pass filters; Cellular neural networks; Circuit testing; Cost function; Energy efficiency; Filter bank; Frequency; Gabor filters; Pixel; Voltage;
Conference_Titel :
Cellular Neural Networks and Their Applications, 2000. (CNNA 2000). Proceedings of the 2000 6th IEEE International Workshop on
Conference_Location :
Catania
Print_ISBN :
0-7803-6344-2
DOI :
10.1109/CNNA.2000.876822