article · Ain Shams Engineering Journal
An automated system for recognising Arabic vehicle number plates has been developed to support smart parking management. The method operates across three primary image processing phases comprising pre-processing, segmentation, and character recognition. Car edges and number plates are isolated using Canny edge detection with variable thresholds, contour detection, and masking techniques. Evaluated on a dataset of 200 images of Egyptian vehicle plates, the identification pipeline achieved an overall recognition accuracy of 93 percent. A working hardware prototype was constructed using ESP32 camera modules paired with a Raspberry Pi. This onboard computing unit also hosts an internal database and a web interface, enabling motorists to locate their parked vehicles by searching for full or partial registration details logged upon entry.
Locating vehicles in large car parks can be challenging, and reading non-Latin scripts such as Arabic often requires specialised recognition tools. By pairing accessible, low-cost microcontrollers with computer vision, this approach provides an efficient way to automate vehicle tracking in parking facilities without relying on expensive, proprietary monitoring hardware.
This technology could be used by commercial car park operators, municipal authorities, and facility managers seeking cost-effective vehicle tracking tools. The system is at an applied and tested prototype stage, running on low-cost ESP32 and Raspberry Pi components, though taking it to market would require validation beyond the initial 200-image evaluation.
AI-generated from the published abstract. Always read the original work before citing.
License Plate Recognition is one of the significant enablers that can be utilized in wide range of applications in ITS and smart cities. The proposed design relies on three image processing stages to achieve license plate identification with high accuracy which are pre-processing, segmentation, and character recognition. The canny edge detection method with various thresholds, contour detection, and masking techniques are used to locate the car edges and license plate. In the experiment presented in this paper, 200 images were used to identify Egyptian car plates. The model successfully identified Arabic license plates with 93% accuracy. A prototype is implemented using ESP32 Cameras and Raspberry-Pi to test the system's performance. Moreover, a database and a website are hosted on the RPi to allow users to search for their car location in the parking lot using the car's full or partial license plate which was saved in database upon detection.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.asej.2023.102178
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
