EALPR: Vehicles - Dataset Ninja

Introduction #

Released 2021-12-09 ·Ahmed Ramadan Youssef, Fawzya Ramadan Sayed, Abdelmgeid Ameen Ali

EALPR: Egyptian Automatic License Plate Recognition (Vehicles) stands as a specialized dataset tailored for object detection purposes, specifically focusing on the identification and localization of license plates. With a compilation of 2084 images, the dataset encompasses a total of 2140 annotated objects, all falling under the singular class of license_plate. Notably, the dataset predominantly features Egyptian License Plates (LP) marked by Arabic digits and characters, showcasing the diversity of license plate styles found across different regions and countries utilizing various scripts, including Latin letters commonly used in Europe, Brazil, the US, and several other locales. This diversity provides an extensive array of examples for training models to recognize and extract license plate information from varying international contexts.

EALPR Structure

EALPR: Vehicles (current)
EALPR: Plates (available on DatasetNinja)

EALPR: Vehicles demo.

EALPR: Plates demo.

Proposed method

Authors use two object detection models for license plate detection and recognition. The input to authors’ proposed system is the vehicle image, whereas the output is the recognized license plate characters and digits. Tiny-YOLOV3 is the backbone architecture for both stages LP detection and recognition.

Main Stages of the Proposed EALPR Approach.

About EALPR

Authors scrap the EALPR dataset images from websites such as Instagram pages and Facebook Marketplace using web scraping Tools. It has 2,450, and 12,160 characters images including many types of vehicles such as cars, buses, trucks, microbuses, and mini-busses. The vehicle images are captured using different cameras, at varying times, lighting, and background.

Characters and Digits Statistics in the EALPR Dataset.

The Egyptian License Plate (LP) uses the Arabic digits and characters which is varying in several countries that use Latin letters such as Europe, Brazil, US, … etc. It has a dimension 16 (height) X 40 (width) with aspect ratio 1:2 approximately. its layout is divided into 3 regions: the country region contains the Egypt word in Arabic and English format, the character region includes plate characters, and the number region contains plate digits. Egyptian License Plate structure uses 10 Arabic digits and 17 Arabic characters.

Egyptian License Plate Structure.

Plate Arabic Digits and Latin Digits.

Plate Arabic Characters and Latin Characters.

After collecting EALPR dataset authors manually annotate the vehicles, characters, and digits using Ybat tool.

Expand

Homepage

Research Paper 1 (main)

Research Paper 2

Summary #

EALPR: Egyptian Automatic License Plate Recognition (Vehicles) is a dataset for an object detection task. It is used in the surveillance industry.

The dataset consists of 2084 images with 2140 labeled objects belonging to 1 single class (license_plate).

Images in the EALPR: Vehicles dataset have bounding box annotations. All images are labeled (i.e. with annotations). There are no pre-defined train/val/test splits in the dataset. The dataset was released in 2021 by the Fayoum University, Egypt and Minia University, Egypt.

Explore #

EALPR: Vehicles dataset has 2084 images. Click on one of the examples below or open "Explore" tool anytime you need to view dataset images with annotations. This tool has extended visualization capabilities like zoom, translation, objects table, custom filters and more. Hover the mouse over the images to hide or show annotations.

Sample annotation mask from EALPR: Vehicles

👀

Have a look at 2084 images

Because of dataset's license preview is limited to 12 images

View images along with annotations and tags, search and filter by various parameters

Class balance #

There are 1 annotation classes in the dataset. Find the general statistics and balances for every class in the table below. Click any row to preview images that have labels of the selected class. Sort by column to find the most rare or prevalent classes.

Rows 1-1 of 1

Class ㅤ	Images ㅤ	Objects ㅤ	Count on image average	Area on image average
license_plate➔ rectangle	2084	2140	1.03	2.22%

Images #

Explore every single image in the dataset with respect to the number of annotations of each class it has. Click a row to preview selected image. Sort by any column to find anomalies and edge cases. Use horizontal scroll if the table has many columns for a large number of classes in the dataset.

Object distribution #

Interactive heatmap chart for every class with object distribution shows how many images are in the dataset with a certain number of objects of a specific class. Users can click cell and see the list of all corresponding images.

Class sizes #

The table below gives various size properties of objects for every class. Click a row to see the image with annotations of the selected class. Sort columns to find classes with the smallest or largest objects or understand the size differences between classes.

Rows 1-1 of 1

Class	Object count	Avg area	Max area	Min area	Min height	Min height	Max height	Max height	Avg height	Avg height	Min width	Min width	Max width	Max width
license_plate rectangle	2140	2.16%	53.78%	0.06%	14px	1.46%	529px	60%	87px	10.01%	26px	3.08%	968px	89.63%

Spatial Heatmap #

The heatmaps below give the spatial distributions of all objects for every class. These visualizations provide insights into the most probable and rare object locations on the image. It helps analyze objects' placements in a dataset.

Objects #

Table contains all 2140 objects. Click a row to preview an image with annotations, and use search or pagination to navigate. Sort columns to find outliers in the dataset.

Rows 1-10 of 2140

Object ID ㅤ	Class ㅤ	Image name click row to open	Image size height x width	Height ㅤ	Height ㅤ	Width ㅤ	Width ㅤ	Area ㅤ
1➔	license_plate rectangle	1843.jpg	960 x 720	76px	7.92%	130px	18.06%	1.43%
2➔	license_plate rectangle	1158.jpg	1080 x 1080	100px	9.26%	186px	17.22%	1.59%
3➔	license_plate rectangle	0006.jpg	720 x 960	68px	9.44%	131px	13.65%	1.29%
4➔	license_plate rectangle	0685.jpg	960 x 960	63px	6.56%	122px	12.71%	0.83%
5➔	license_plate rectangle	1895.jpg	960 x 540	66px	6.88%	95px	17.59%	1.21%
6➔	license_plate rectangle	0301.jpg	640 x 640	17px	2.66%	26px	4.06%	0.11%
7➔	license_plate rectangle	0301.jpg	640 x 640	38px	5.94%	70px	10.94%	0.65%
8➔	license_plate rectangle	0562.jpg	1512 x 1280	134px	8.86%	242px	18.91%	1.68%
9➔	license_plate rectangle	0347.jpg	1125 x 900	96px	8.53%	182px	20.22%	1.73%
10➔	license_plate rectangle	1592.jpg	720 x 960	89px	12.36%	203px	21.15%	2.61%

License #

License is unknown for the Egyptian Automatic License Plate Recognition: Vehicles dataset.

Source

Citation #

If you make use of the EALPR: Vehicles data, please cite the following reference:

@INPROCEEDINGS{9845514,
  author={Youssef, Ahmed Ramadan and Sayed, Fawzya Ramadan and Ali, Abdelmgeid Ameen},
  booktitle={2022 7th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)}, 
  title={A New Benchmark Dataset for Egyptian License Plate Detection and Recognition}, 
  year={2022},
  volume={},
  number={},
  pages={106-111},
  doi={10.1109/ACIRS55390.2022.9845514}
}

Source

If you are happy with Dataset Ninja and use provided visualizations and tools in your work, please cite us:

@misc{ visualization-tools-for-ealpr-vehicles-dataset,
  title = { Visualization Tools for EALPR: Vehicles Dataset },
  type = { Computer Vision Tools },
  author = { Dataset Ninja },
  howpublished = { \url{ https://datasetninja.com/ealpr-vehicles } },
  url = { https://datasetninja.com/ealpr-vehicles },
  journal = { Dataset Ninja },
  publisher = { Dataset Ninja },
  year = { 2024 },
  month = { nov },
  note = { visited on 2024-11-21 },
}

Download #

Please visit dataset homepage to download the data.

. . .

Disclaimer #

Our gal from the legal dep told us we need to post this:

Dataset Ninja provides visualizations and statistics for some datasets that can be found online and can be downloaded by general audience. Dataset Ninja is not a dataset hosting platform and can only be used for informational purposes. The platform does not claim any rights for the original content, including images, videos, annotations and descriptions. Joint publishing is prohibited.

You take full responsibility when you use datasets presented at Dataset Ninja, as well as other information, including visualizations and statistics we provide. You are in charge of compliance with any dataset license and all other permissions. You are required to navigate datasets homepage and make sure that you can use it. In case of any questions, get in touch with us at hello@datasetninja.com.