Hardware edge detection system based on a self-assembled vertically aligned ferroelectric memristor
Abstract
Real-time image processing faces significant challenges in traditional von Neumann systems due to data transfer bottlenecks between the processor and memory. Neuromorphic computing offers a promising alternative. This study introduces a self-assembled, vertically aligned ferroelectric memristor based on Ba0.6Sr0.4TiO3:(ZrO2)0.92(Y2O3)0.08 (BST:YSZ) for electronic synaptic functions. The memristor demonstrates stable, tunable resistance states that effectively mimic synaptic behavior. Using its neuromorphic architecture, we developed an image edge detection system. The system's output closely matches simulation results, achieving a mean square error of 3.88, a peak signal-to-noise ratio of 27.88 dB, and a structural similarity index of 0.97, indicating high computational accuracy. These findings highlight the potential of ferroelectric memristors for neuromorphic edge computing, particularly in real-time image processing applications.
Article Details
Journal Info
Applied Physics Letters
American Institute of Physics
Authors (8)
Biao Yang
State Key Laboratory of Fine Chemicals, Frontiers Science Center for Smart Materials Oriented Chemical Engineering, School of Chemical Engineering
Zelei Jiao
Key Laboratory of Brain-Like Neuromorphic Devices and Systems of Hebei Province, College of Electron and Information Engineering, Hebei University , Baoding 071002,
Junfeng Yu
Key Laboratory of Brain-Like Neuromorphic Devices and Systems of Hebei Province, College of Electron and Information Engineering, Hebei University , Baoding 071002,
Yazhen Meng
Key Laboratory of Brain-Like Neuromorphic Devices and Systems of Hebei Province, College of Electron and Information Engineering, Hebei University , Baoding 071002,
Jialiang Yang
Pengfei Li
Weifeng Zhang
Xiaobing Yan