An Efficient FPGA-Based Architecture for Convolutional Neural Networks

The goal of this paper is to implement an efficient FPGA-based hardware architectures for the design of fast artificial vision systems. The proposed architecture is capable of performing classification operations of a Convolutional Neural Network (CNN) in realtime. To show the effectiveness of the architecture, some design examples such as hand posture recognition, character recognition, and face recognition are provided. Experimental results show that the proposed architecture is well suited for embedded artificial computer vision systems requiring high portability, high computational speed, and accurate classification.