Microcomb-Driven Optical Convolution for Car Plate Recognition
نویسندگان
چکیده
The great success of artificial intelligence (AI) calls for higher-performance computing accelerators, and optical neural networks (ONNs) with the advantages high speed low power consumption have become competitive candidates. However, most reported ONN architectures demonstrated simple MNIST handwritten digit classification tasks due to relatively precision. A microring resonator (MRR) weight bank can achieve a high-precision matrix increase density assistance wavelength division multiplexing (WDM) technology offered by dissipative Kerr soliton (DKS) microcomb sources. Here, we implement car plate recognition task based on an convolutional network (CNN). An integrated DKS was used drive MRR weight-bank-based photonic processor, precision one convolution operation could reach 7 bits. first layer realized in domain, remaining layers were performed electrical domain. Totally, optoelectronic system (OCS) comparable performance 64-bit digital computer character classification. error distribution obtained from experiment emulate other layers. probabilities softmax slightly degraded, robustness CNN reduced, but results still acceptable. This work explores OCS driven realize real-life time provides promising computational acceleration scheme complex AI tasks.
منابع مشابه
Algorithm for License Plate Localization and Recognition for Tanzania Car Plate Numbers
In this paper, License plate localization and recognition (LPLR) is presented. It uses image processing and character recognition technology in order to identify the license number plates of the vehicles automatically. This system is considerable interest because of its good application in traffic monitoring systems, surveillance devices and all kind of intelligent transport system. The objecti...
متن کاملVideo-based Car Surveillance: License Plate, Make, and Model Recognition
OF THE THESIS Video-based Car Surveillance: License Plate, Make, and Model Recognition
متن کاملAutomatic Car Plate Recognition Using a Partial Segmentation Algorithm
In this paper we present a new method for car plate recognition. In the past [1] [2], our group has worked extensively in this problem and one of our main conclusions was that segmentation was responsible for most part of the system errors. This upgrade is based on the simple idea of not performing a full segmentation in order to reduce errors. As we will explain along the paper, the new method...
متن کاملMulti-frame Super Resolution for Improving Vehicle Licence Plate Recognition
License plate recognition (LPR) by digital image processing, which is widely used in traffic monitor and control, is one of the most important goals in Intelligent Transportation System (ITS). In real ITS, the resolution of input images are not very high since technology challenges and cost of high resolution cameras. However, when the license plate image is taken at low resolution, the license...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Photonics
سال: 2023
ISSN: ['2304-6732']
DOI: https://doi.org/10.3390/photonics10090972