Affiliation:
1. State Key Laboratory for Superlattices and Microstructures Institute of Semiconductors Chinese Academy of Sciences Beijing 100083 China
2. Center of Materials Science and Optoelectronic Engineering University of Chinese Academy of Sciences Beijing 100049 China
Abstract
AbstractThe image degradation owing to the absorption and scattering of optical propagation medium makes the non‐visualization and anamorphose in real image. The complex algorithms based on highly integrated hardware can restore degraded image while it causes inefficient serial operation and storage redundancy. One improved strategy is to parallel functional integration in front‐end visual perceptron. Here, a parallel photoelectron storage and visual preprocessing in nanowire perceptron to synchronously achieve image perception, visual memory, and in‐sensor preprocessing are demonstrated. This functional integration is originated from charge‐resolved storage in temporal or frequency domain under optical pulsed excitation due to cascaded defect engineering. The proposed system enhances the peak signal‐to‐noise ratio (PSNR) of degraded image from 152 to 181 dB by feature decompression and also has 7.2% of PSNR improvement by noise filtration. This system is validated to improved train accuracy of back‐end artificial neural network (ANN) by 32.8% and shorten its iteration period by 77.4%.
Funder
National Natural Science Foundation of China
Youth Innovation Promotion Association of the Chinese Academy of Sciences
Subject
Electrochemistry,Condensed Matter Physics,Biomaterials,Electronic, Optical and Magnetic Materials
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献