A nano-functional-device-based image feature extraction circuitry with current-balancing feedback

An image feature extraction VLSI architecture using resonance current-voltage (I-V) characteristics has been proposed aiming at demonstrating a new potentiality of nano functional devices for use in building human-like intelligent systems. In this work, the resonance characteristics of nano devices have been emulated by CMOS inverter-based convolution circuits and directional edge filtering was carried out by subthreshold operation of CMOS circuits. In order to retain only essential features in the input image, a current-balancing feedback circuitry has been explored. The circuit can select relatively significant edges and leave them as digital flags autonomously. In order to verify the concept, a small-scale circuit was designed in a standard 0.18-mum CMOS technology, and its correct operation was confirmed by SPICE simulation.