English 한국어 日本語 Tiếng Việt

😍TS-ANPR

TS-ANPR is a deep learning-based vehicle license plate recognition engine that supports the license plate standards of Korea, Japan, and Vietnam.

✨ Application Example (TS-IVR)
😍 Live Demo 👈 Check the number recognition performance directly here.
🚀 Download the Latest Engine
🎨 Code Samples in Popular Languages
📖 Application Development Guide
🎁 How to install
⚖️ License

If you have any questions or requests, please feel free to open an Issues. We are happy to assist and welcome your feedback!

Table of Contents


Latest Version Information

Release v3.1.2 (2025.8.29)🎉

  1. Fixed a potential crash issue that could occur when the engine was initialized with the ‘sync’ parameter and license plate recognition was invoked concurrently from multiple threads.

Release v3.1.1 (2025.8.18)🎉

  1. Fixed: There was an issue where vehicles without visible license plates were excluded from the results when using the dr option to detect both vehicles and license plates, and it has been fixed.

Release v3.1.0 (2025.8.1)🎉

  1. Improved Recognition Accuracy
    • The recognition accuracy for Japanese and Korean license plates has been enhanced.

Deep Learning Model Types and Their Applications

Licenses apply to all deep learning models, so you just need to select the model that best fits your intended purpose.

Model Recognition Speed Application Examples
S Fast
(for short range)		 Parking lot entry and exit management
M Normal
(for mid range)		 Parking space occupancy management / Parking location search

Fisheye lens camera (360° surround recognition)

Overturned vehicle (360° surround recognition)
L Slow
(for long range)		 Large outdoor parking lot / Vehicle counting

Multi-lane vehicle license plate recognition

Traffic volume counting

Comparison Table of Recognition Speed by Deep Learning Model

CPU Cores Threads Clock(1) OS S(2) M(2) L(2)
Intel i7-12700 12 20 2.1 64-bit Windows
64-bit Linux		 0.021 0.036 0.054
Intel i5-6500 4 4 3.2 64-bit Windows
64-bit Linux		 0.031 0.078 0.140
(Same)       32-bit Windows 0.078 0.172 0.296
Intel i3-8100 4 4 3.6 64-bit Windows
64-bit Linux		 0.042 0.087 0.156
(Same)       32-bit Windows 0.089 0.204 0.656
Intel Celeron J4005 2 2 2.0 64-bit Windows
64-bit Linux		 0.396 0.886 1.563
(Same)       32-bit Windows 0.629 1.355 2.368
Intel Celeron 1037U(3) 2 2 1.8 32-bit Windows 0.484 1.061 1.856
Rockchip RK3588S(4) 8 8 1.5 64-bit Linux 0.227 0.462 0.842
Broadcom BCM2711(5) 4 4 1.8 64-bit Linux 0.465 1.024 1.817

Key Features

1. License plate recognition performance

Has excellent adaptability to various environmental factors below.

2. Supports various license plate formats

Supports various license plate formats as shown below.

3. Supported operating systems / CPU architectures

4. Supports various development environments

5. Various license options available

Various Recognition Options

1. Inspection of Vehicle-mounted License Plates

Distinguishes whether a license plate is mounted on a vehicle in images where the vehicle body is visible. When the Vehicle-mounted (v) option is enabled, only license plates attached to vehicles are recognized.

License plates without vehicles, such as standalone plates or motorcycle plates as shown in the image below, are ignored.

[Image source: 연합뉴스]

</img>


[Image source: 바이커즈랩]

</img>


If only the license plate is photographed up close, vehicle recognition may not work. In such cases, if the Vehicle-mounted (v) option is not used, the license plate number can still be recognized.

2. Multiple Recognition

When the Multiple Recognition (m) option is enabled, all vehicles in the image are recognized.

If the Multiple Recognition (m) option is not used, only the license plate with the highest confidence (most visible) among multiple vehicles will be recognized.

3. 360° Surround Recognition

When the 360° Surround Recognition (s) option is enabled, license plates can be recognized even if vehicles in the image are tilted or overturned in various directions, such as overturned vehicles or those captured with a fisheye lens camera.

[Image source: KBS]

</img>


4. Object Detection

When the Object Detection (d) option is enabled, objects in the image are detected. By comparing the detected vehicle area with the parking space area set in the application, it is possible to determine whether the space is occupied or vacant.

5. License Plate Recognition of Detected Objects (Vehicles)

When both Object Detection (d) and License Plate Recognition (r) options are enabled, the license plates of detected vehicles are also recognized.

5. Setting Region of Interest and Minimum License Plate Size

By combining the settings for Region of Interest (i), Exclusion Zone (x), and Minimum License Plate Size (a), you can prevent license plate recognition for vehicles outside the designated area.