ANPR technology has surged in popularity in recent years due to its wide range of benefits for various applications. Traffic management, intelligent parking, toll automation, intelligent transportation systems in smart cities, and journey time analysis are just a few of the advantages that ANPR offers.
Our Background: We power the computer vision development platform Viso Suite that leading organizations worldwide use to build, deploy and scale their computer vision applications. Viso provides a no-code platform to build AI systems for ANPR, vehicle counting, and traffic analysis. Request a demo for your organization!
In the following, we will share our hands-on insights and practical concepts of automatic number plate recognition. In particular, this article covers:
- What is ANPR?
- How does ANPR work to identify vehicles?
- The best ANPR software and techniques
- Advantages of automated plate recognition
What Is ANPR?
Automatic Number Plate Recognition (ANPR) is a technology that uses optical character recognition on images of vehicle registration plates to read the vehicle’s registration number. An automatic license plate recognition system applies different image processing techniques to quickly and automatically identify vehicles in video or photo footage from cameras.
Automatic License Plate Recognition System
An automatic license plate recognition system can be used for a variety of purposes, such as tracking the movement of vehicles, identifying specific cars, automated parking enforcement, and so on.
The use of ANPR systems is becoming more popular as the technology advances rapidly with the advent of machine learning and deep learning, the computational cost decreases, and the accuracy of applied image processing techniques increases.
ANPR System Types
There are two primary types of ANPR systems:
- Fixed systems: Fixed ANPR systems are those that are installed at a specific location and point in time. For example, these systems may be installed at toll booths, border crossings, or other strategic locations.
- Mobile systems: Mobile ANPR systems are those that are carried by a vehicle and can be used to scan the registration plates of other vehicles. For example, these systems may be used by police cars to track down wanted vehicles.
How Does ANPR Work?
Automated number plate recognition (ANPR) systems apply optical character recognition (OCR) in combination with other image processing techniques to read vehicle registration plates.
ANPR is one of the most accurate and widely applied computer vision systems, the used techniques are constantly evolving to increase performance, accuracy, cost-efficiency, robustness, and scalability of automatic license plate recognition software.
There are a few different techniques popularly used in ANPR which are used in combination as part of the computer vision pipeline. The vision pipeline contains the steps required to transform image or video input into meaningful full information.
Those are the most important components:
Real-time object detection
Object detection uses deep learning to recognize vehicles and different vehicle classes (bus, truck, car, van, motorcycle, etc.) in images of video streams. State-of-the-art object detection algorithms such as YOLOv3 or YOLOv7 use neural networks trained on a dataset of images.
Image Processing includes traditional computer vision methods used to normalize and prepare images for being processed by the OCR algorithm. Since ANPR applications are usually used in challenging real-world environments with varying illumination, occlusion, weather, and inconsistent set-ups, image processing functions are used to sharpen, color-correct, or crop images to significantly improve the results and output of subsequent algorithms.
OpenCV is one of the most widely used libraries for image processing tasks in ANPR systems.
Optical Character Recognition (OCR)
Optical Character Recognition (OCR) is an important computer vision technique for reading text from images. This allows the ANPR system to identify license plates. Image processing techniques such as Tesseract OCR or MaskOCR algorithms are used to detect individual characters, verify the sequence of those characters, and convert the number plate image to text.
Template matching is a technique to compare an image of a license plate against a library of images of license plates to find a match. Template matching is a technique for finding a specific pattern in a text string. In the case of ANPR, the set of characters are the vehicle number plates.
How to test ANPR with Deep Learning
Here is an easy way to test a demo of ANPR with YOLOv7, one of the best-performing computer vision models which was released in July 2022.
- Step 1: You can access the pre-trained ANPR model here
- Step 2: Upload your images and videos for testing.
Typical ANPR systems include a digital image capture unit (camera), a processing unit, and different algorithms for video analytics.
- Video input and image acquisition: Firstly, the ANPR camera captures images or videos that contain one or multiple license plates (video stream or photo). Often, infrared lighting is used to allow cameras to capture vehicle registration plates at night, making it possible to operate ANPR at all hours of the day.
- Detect and crop number plate: In the image, the license plate is detected using machine learning and computer vision methods. There are different methods that differ significantly in terms of computing resources needed, complexity, speed, and accuracy. A common method includes firstly detecting the vehicles using object detection, then localizing the numberplate within those bounding boxes. This is usually achieved by finding areas of contrast between the background and the numberplate. Once the number plate is detected, it is cropped and normalized (sharpened, distorted and enhanced).
- Extract and read number plate: Next, OCR software is applied to the detected plate area to return the license plate number in text format. The OCR software can be optimized for different character sets, making it possible to use the same ANPR system in different countries. The output of an ANPR system is typically the license plate number, often with the region or country identifier.
- Use number plate information: Finally, once converted into plain text format, the vehicle plate number is stored in a database for integration with other IT systems. It can be used to compare the license plate to a database of registered plates, or whitelist and blacklist databases. If found in the database, the software returns stored information about the vehicle, for example, name and address of the registered owner.
Benefits of Automatic Number Plate Recognition
ANPR offers numerous advantages that are the basis for real-world applications. Most benefits of ANPR come with automating manual tasks, highly efficient space management, governance, and increasing the customer experience.
- Automation: The automated recognition of number plates allows automated alerts and controls for facilities. Hence, ANPR is a key technology for smart cities or toll stations.
- Accuracy: ANPR systems can achieve very high accuracy, and can quickly and easily identify vehicles by their license plates.
- Analytics: The generated data can be used for traffic flow analytics. This is particularly important for operating Intelligent Transportation Systems (ITS), where data processing technologies are used to improve the mobility of people and goods, demand management, increase safety, reduce traffic congestion and manage incidents effectively.
- Identification: Fast recognition of a vehicle numberplate is the basis for fast and seamless vehicle identification. The identification can be used to grant vehicles access or find and track specific vehicles.
- Cost-Efficiency: The precise and fast number plate recognition doesn’t rely on human input. Large numbers of license plates can be analyzed very quickly, making it a very efficient method to identify vehicles. Hence it drives cost-efficient governance and reduces waiting times.
- Low Footprint: An automated numberplate recognition system is relatively cost-effective to install and operate. A wide range of cameras is suitable for ANPR.
- Scalability: The use of emerging technologies such as IoT (or AIoT) and Machine Learning at the Edge (Edge AI) enable the development of distributed systems. Edge computing makes it possible to implement offline capabilities, private and cost-efficient video analytics required for ANPR.
- Convenience: ANPR is usually integrated with other IT systems and operates in an ecosystem to provide a seamless and hassle-free experience to the end-users. Hence, the technology is used to enhance the customer experience and offer new services and products, such as automated parking payments.
- Versatility: Automated vehicle identification can be applied for a variety of applications, from parking management to security, traffic enforcement, logistics optimization in manufacturing, and so on.
- Security: ANPR solutions are of great importance for various security and surveillance applications of computer vision. Such systems help improve security by providing a method to identify and track multiple vehicles autonomously.
- Environmental benefits: The use of an ANPR system can help reduce traffic congestion and pollution by discouraging unnecessary driving. Reducing waiting times, or time to search for parking spaces in cities helps decrease the environmental pollution.
Popular Use Cases of ANPR
Automatic number plate recognition is essential for a wide range of applications, where the detection, identification, or localization of vehicles is important. Read our extensive article about other use cases of computer vision in smart city applications.
Police forces use ANPR for law enforcement purposes, to check if a vehicle is registered, or to identify vehicles related to traffic violations. The ability to detect and recognize number plates in real-time allows authorities to identify vehicles and track their location.
Smart parking management
Car parking management requires an integrated solution to detect individual vehicles. Hence, automated number plate recognition is the key to efficient car parking management. ANPR allows parking garages to have automated parking management because every car is accounted for by its license plate number. Such intelligent parking systems keep track of every vehicle in the facility and ensure complete governance.
As a result, parking garage users can avoid the stress of managing their own tickets and tracking time spent, risking penalties for inaccurate ticket payments or losing their tickets. In addition, automated surveillance can be referred back to in case of a disagreement.
Journey time analysis
Journey time analysis (JTA) is a crucial application for authorities to identify passing through vehicles and their time from one node to another. In addition, such analytics allow better route planning for traffic administrators.
Intelligent traffic management
Traffic management is the umbrella term for a plethora of advantages that ANPR offers. Automated vehicle number plate detection can be used throughout cities to detect overspeeding vehicles, vehicles that drive rashly, or any accidental occurrence.
ANPR provides solutions for measuring and analyzing area-related traffic data of a certain area or an entire city. On a larger scale, traffic management allows insights into traffic congestion for better traffic planning.
Retail park security
Retail parks often deal with unauthorized parking, leading to hassles for rightful parking spaces or sometimes suspicious activities. Such security risks can be addressed with ANPR technology by ensuring only authorized vehicles are using parking spaces.
Manual tollbooth management on highways is still a significant practice in some parts of the world. Often, automated toll stations leverage different technologies for autonomous tollbooth management. For example, on larger freeways, ANPR allows authorities to receive license plate numbers for paying tolls by mail or automatically rather than stopping and paying at a manually-run tollbooth. Hence, ANPR enables efficient toll booth management, and dynamic road pricing, and allows decreasing the operational time needed, thus increasing productivity.
Get Started with your ANPR Project
If your organization is looking to build an enterprise ANPR system that uses the latest and most powerful algorithms and integrates with existing cameras and databases – check out Viso Suite.
Viso Suite is the most comprehensive computer vision platform that provides a workspace with software infrastructure for large-scale license plate recognition. It provides Edge AI for distributed computer vision and provides no-code automation throughout the entire application lifecycle.
Get in touch to learn more about our ANPR solution and explore the Viso Suite whitepaper to see what makes Viso the most powerful computer vision platform today.
ANPR is a crucial AI vision technology that offers many advantages for various applications. The benefits of ANPR are wide-ranging and include traffic management, retail park security, toll booth records, and journey time analysis. As such, it’s no wonder that ANPR has become so popular in recent years, the global automatic number plate recognition market is rapidly growing, and we see disruptive ANPR projects across industries such as transportation, logistics, security, and the public sector.
If your organization is looking to take advantage of this powerful technology, be sure to get in touch with us. We offer a comprehensive computer vision platform that provides everything you need to build an enterprise-level ANPR system.
To learn more about related topics in image recognition, we recommend you the following articles:
- The Most Valuable Computer Vision Smart City Applications
- Computer Vision In Manufacturing. The 10 Most Popular Applications
- Read an easy-to-understand guide about Computer Vision
- Learn about Object Detection with Computer Vision
- Explore an extensive list of Computer Vision Applications