A miniature entry-station model that reads plates with YOLO and OCR, checks them against a database, opens a servo barrier via NodeMCU, and sends toll and violation messages.
A project to develop a miniature smart border-station model that recognizes vehicle license plates using computer vision and optical character recognition (OCR), then compares the plate number with a database of authorized vehicles to decide automatically whether to open the barrier or keep it closed. The project was carried out by a team of students with technical assistance from Techno Enjaz.
The system combines a Python program that uses the YOLO algorithm to locate the plate and OCR to read it with a NodeMCU ESP8266 board that controls a barrier driven by an MG995 servo, plus an infrared sensor that detects an approaching vehicle, LED indicators, and automatic messages sent through an HC-05 Bluetooth module to an app on a receiving device, reporting toll deductions, violations, or a wanted vehicle. The project provides a functional proof of concept on a miniature model, without published numerical measurements of reading accuracy.
| Item | Details |
|---|---|
| Project type | Miniature access-control model based on license plate recognition |
| Field | Computer vision, automatic license plate recognition (ALPR), embedded systems |
| Project status | Working miniature entry-station model |
| Techno Enjaz role | Technical support and assistance to the students during project development |
| Core technologies | Python, YOLO, OCR, NodeMCU ESP8266, MG995 servo, IR sensor, HC-05 Bluetooth |
| Outputs | Plate number reading, pass or deny decision, automatic barrier opening, LED indicators, toll, violation, and alert messages |
Traditional verification at entry points and border crossings relies on human intervention for checks and inspection, which makes it prone to error and delay, especially when an unauthorized vehicle requires an immediate response. The project aims to automate the check of a vehicle's right to enter by reading its plate and comparing it with a database, using a low-cost solution that does not need complex infrastructure.
The project was carried out academically by the students, with technical assistance and support from Techno Enjaz during development. It is presented among the office's work as an example of its support for projects that connect computer vision with electronic control in a single physical model.
| Component | Role in the model |
|---|---|
| Camera | Captures the vehicle's plate image |
| Computer running the Python program | Detects the plate with computer vision, reads it with OCR, and compares it with the database |
| NodeMCU ESP8266 | Receives the entry decision and controls the barrier and indicators; 80 MHz (or 160 MHz) processor with Wi-Fi |
| MG995 servo | Opens and closes the entry barrier; about 10 kg·cm torque, about 180 degrees of travel, 4.8–7.2V supply |
| IR obstacle sensor | Detects the approaching vehicle; short adjustable range of roughly 2–30 cm |
| DC-DC step-down regulator | Lowers and stabilizes the supply voltage for the components |
| LED indicators (green and red) | Indicate pass or deny |
| HC-05 Bluetooth module | Sends notifications to the app on the receiving device |
| Resistors | Protect components and limit current |
The report shows examples of automatic messages sent by the model, including:
In the built model these messages reach an app on a nearby device over Bluetooth, so they simulate the notification channel rather than providing a real link to messaging systems or official authorities.
The miniature model successfully carried out the full cycle: detecting the approaching vehicle, capturing and reading the plate, making the entry decision, opening the barrier or keeping it closed, showing the appropriate light indicator, and sending toll, violation, and alert messages.
The report describes the system as fast and accurate under varied lighting and plate styles, but it gives no numerical measurements of plate-reading accuracy, processing time, or the number of plates tested. The high accuracy figures in the literature review chapter (such as above 95% or 99%) come from other published studies and are not results of this project.
According to the directions set out in the project:
Systems of this kind handle plate numbers, owner data, and violations, so any real deployment requires a clear legal framework, defined access rights, and protection of stored and transmitted data.
If you are working on an automated access-control or computer vision system and need technical help developing the idea or building a prototype, you can contact the Techno Enjaz office to discuss the project's requirements and the appropriate scope of support.
A miniature smart border-station model that recognizes vehicle license plates using computer vision and OCR and compares them with a database of authorized vehicles to decide automatically whether to open the barrier or keep it closed. It was built by a team of students with technical assistance from Techno Enjaz.
An infrared sensor detects the approaching vehicle and the camera captures the plate; a Python program locates it with YOLO, reads the number with OCR, and checks it against the database. If allowed, the servo opens the barrier and a green LED lights; if denied, the barrier stays closed, a red LED lights, and an alert is sent.
A camera and a computer running the Python computer vision and OCR program, a NodeMCU ESP8266 board, an MG995 servo for the barrier, an IR sensor for approach detection, a DC-DC regulator, green and red LED indicators, an HC-05 Bluetooth module for notifications, and resistors.
It sends automatic messages for toll deductions, warnings that registration and insurance are about to expire, violations for not renewing them, and an alert when a wanted vehicle is detected asking to inform the nearest police point. In the model, messages reach an app on a nearby device via Bluetooth, simulating the notification channel.
The miniature model carried out the full cycle from detecting the vehicle and reading the plate to opening the barrier and sending messages, but the report gives no numerical measurements of reading accuracy or processing time. Its limits include a single miniature gate, a local database, and Bluetooth notifications with no link to official systems.
Reach out to Techno Enjaz engineering team to discuss technical feasibility, prototype hardware, and development scope.
Discover more engineering prototypes and academic implementations
A virtual board for writing, drawing, picking colors and erasing with hand gestures in front of a camera, built in Python with MediaPipe hand tracking and OpenCV.
A prototype that detects people with YOLOv8 and tracks them with DeepSORT in defined work areas, counts presence time in seconds, and exports records to Excel.
An exam-monitoring prototype using YOLO, MediaPipe and OpenCV to analyze a student's head direction, flagging head turns in red for review and forward gaze in green.
