LPRNet: License Plate Recognition via Deep Neural Networks

Zherzdev, Sergey; Gruzdev, Alexey

doi:10.48550/arxiv.1806.10447

Cited by 19 publications

(26 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Faster RCNN, [12], and LPRNet, [13], are closely related to our work. Two subnets of GRCNN are built following their ideas.…”

Section: Introductionmentioning

confidence: 60%

GRCNN: Graph Recognition Convolutional Neural Network for Synthesizing Programs from Flow Charts

Cheng¹,

Yang²

2020

Preprint

View full text Add to dashboard Cite

Program synthesis is the task to automatically generate programs based on user specification. In this paper, we present a framework that synthesizes programs from flow charts that serve as accurate and intuitive specifications. In order doing so, we propose a deep neural network called GRCNN that recognizes graph structure from its image. GRCNN is trained end-to-end, which can predict edge and node information of the flow chart simultaneously. Experiments show that the accuracy rate to synthesize a program is 66.4%, and the accuracy rates to recognize edge and nodes are 94.1% and 67.9%, respectively. On average, it takes about 60 milliseconds to synthesize a program.

show abstract

“…Faster RCNN, [12], and LPRNet, [13], are closely related to our work. Two subnets of GRCNN are built following their ideas.…”

Section: Introductionmentioning

confidence: 60%

GRCNN: Graph Recognition Convolutional Neural Network for Synthesizing Programs from Flow Charts

Cheng¹,

Yang²

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…To the best of our knowledge, all the approaches use object detection based methods for stage 1, the object detection poses challenges in cases of tilted number plates, where the cropped plates will have a lot of irrelevant information. [3] uses spatial transformer network [8] to preprocess the cropped license plate image which helps in improving the results. One other solution can be to detect four separate points of plates, and use these 4 points with perspective transform to finally get a warped image.…”

Section: Related Workmentioning

confidence: 99%

“…Although, the primary benefit of object detection over semantic segmentation is annotation time, but since for this task to annotate semantic segmentation polygons only 4 points are required (unlike the usual semantic masks which requires multiple vertices in the polygon), it is not much overhead over the basic rectangle-based object detection annotations. We crop the plates detected by any detection method and recognize them using LPRNet [3] trained on our dataset. These models are individually described below.…”

Section: Modelmentioning

confidence: 99%

See 1 more Smart Citation

Indian Licence Plate Dataset in the wild

Tanwar¹,

Tiwari²,

Chowdhry³

2021

Preprint

View full text Add to dashboard Cite

Indian Number (Licence) Plate Detection is a problem that has not been explored much at an open-source level. There are proprietary solutions available for it, but there's no big enough open-source dataset that can be used to perform experiments and test different approaches. Most of the large datasets available are for countries like China [1], Brazil [2], but the model trained on these datasets do not perform well on Indian plates because the font styles and plate designs used vary significantly from country to country. This paper introduces an Indian Number (license) plate dataset with 16,192 images and 21,683 plate plates annotated with 4 points for each plate and each character in the corresponding plate.We propose a two-stage approach in which the first stage is for localizing the plate, and the second stage is to read the text in cropped plate image. We present a model that uses semantic segmentation to solve number plate detection. We tested object detection and semantic segmentation model; for the second stage, we used lprnet [3] based OCR. Data, codes and demo are available here: https://github.com/sanchit2843/Indian LPR

show abstract

“…Many color-based methods (Shi et al, 2005;Chen et al, 2009) usually use the combination of the license plate and the characters. However, since the two-stage methods are not only slow to run, but also take more time to converge for optimized training due to the double networks, one-stage pipeline based methods, segmentation-free approach (Zherzdev and Gruzdev, 2018;Cheang et al, 2017;Li and Shen, 2016;, including segmentation and recognition at once, are proposed. Most segmentation-free models take advantage of deeply learned features which outperforms traditional methods on the task of classification by deep convolutional neural networks (DCNN) (Simonyan and Zisserman, 2014;He et al, 2016) and data-driven approaches (Russakovsky et al, 2015).…”

Section: License Plate Recognitionmentioning

confidence: 99%

Practical License Plate Recognition in Unconstrained Surveillance Systems with Adversarial Super-Resolution

Lee

Jun

Hong

et al. 2019

Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

Although most current license plate (LP) recognition applications have been significantly advanced, they are still limited to ideal environments where training data are carefully annotated with constrained scenes. In this paper, we propose a novel license plate recognition method to handle unconstrained real world traffic scenes. To overcome these difficulties, we use adversarial super-resolution (SR), and one-stage character segmentation and recognition. Combined with a deep convolutional network based on VGG-net, our method provides simple but reasonable training procedure. Moreover, we introduce GIST-LP, a challenging LP dataset where image samples are effectively collected from unconstrained surveillance scenes. Experimental results on AOLP and GIST-LP dataset illustrate that our method, without any scene-specific adaptation, outperforms current LP recognition approaches in accuracy and provides visual enhancement in our SR results that are easier to understand than original data.

show abstract

LPRNet: License Plate Recognition via Deep Neural Networks

Cited by 19 publications

References 0 publications

GRCNN: Graph Recognition Convolutional Neural Network for Synthesizing Programs from Flow Charts

GRCNN: Graph Recognition Convolutional Neural Network for Synthesizing Programs from Flow Charts

Indian Licence Plate Dataset in the wild

Practical License Plate Recognition in Unconstrained Surveillance Systems with Adversarial Super-Resolution

Contact Info

Product

Resources

About