Image processing using SETMOS-based CNN

An implementation method of cellular neural networks (CNN) based on a novel complimentary metal-oxide-semiconductor (CMOS) and single electron transistor (SET) hybrid structure named SETMOS, is proposed in this paper. The main building blocks including cell core circuit, feedback template and control template circuits are designed by the characteristic of negative differential resistance (NDR) of SETMOS and current mirror. Finally, a CNN is constructed and applied in image processing on connected component detector (CCD) and shadow detector (SD). The computer simulation results show that the designed SETMOS CNN circuits, compared to traditional CNN hardware circuits, are suitable for various scale CNN implementation because of simpler structure, lower power dissipation, faster response and higher integrated density. To a certain degree, this kind of designed structure makes it practicability and reliability in image processing.