Reading car license plates using deep neural networks

Li, Hui; Wang, Peng; You, Mingyu; Shen, Chunhua

doi:10.1016/j.imavis.2018.02.002

Cited by 160 publications

(205 citation statements)

References 42 publications

Supporting

Mentioning

198

Contrasting

Unclassified

Order By: Relevance

“…Then we take license plate image and split it in windows using sliding window approach (figure 5.). Unlike (Li H. & Shen C., 2016) and (He P. et al, 2016), the width and height of our sliding window are not equal -this is because the height and width of the license plate symbols are also different. Therefore we adjust the window width to 24 pixels, so the window size corresponds to symbol width/height ratio.…”

Section: Reading License Platementioning

confidence: 85%

“…The recognition of localized license plates proposed in this paper is mostly based on the approach in (Li H. & Shen C., 2016). We use the same main workflow with CNN and a Recurrent Neural Network (RNN).…”

Section: Related Workmentioning

confidence: 99%

“…For example, RNNs have achieved great results on speech recognition (Hannun A. et al, 2014) and image captioning (Xu K. et al, 2015). In (Li H. & Shen C., 2016) a CNN is used to acquire sequence of features corresponding to reading license plate from left to right. In this paper we further extended the functionality of this approach, inspired by papers (He P. et al, 2016) and (Shelhamer E. et al, 2017).…”

Section: Related Workmentioning

confidence: 99%

“…The architecture of maxout CNN from (He P. et al, 2016) had to be modified to best fit our exact problem. The specific type of RNN used for sequence reading in (Li H. & Shen C., 2016) and in the current paper is the Long Short-Term Memory (LSTM) proposed in (Hochreiter S., & Schmidhuber J., 1997). It is known for its ability of dealing with RNN training problems -vanishing and exploding gradients.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

The impact of knowledge management, learning and socio-cultural factors on innovation

Baranova¹

2017

International Scientific Conference "New Challenges of Economic and Business Development – 2017. Digital Economy" : Proceedings

View full text Add to dashboard Cite

Section: Reading License Platementioning

confidence: 85%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

The impact of knowledge management, learning and socio-cultural factors on innovation

Baranova¹

2017

International Scientific Conference "New Challenges of Economic and Business Development – 2017. Digital Economy" : Proceedings

View full text Add to dashboard Cite

“…In the last few years, LPR has been widely studied in theoretical, experimental and numerical ways to provide robust image representation. Many LPR methods [2,1,11,20] are capable of capturing the structural properties of images and noise for carefully constrained settings. Despite the recent success, recognizing license plate in the wild is still far from satisfactory due to the variations that suffer from appearance, noise, angle, and illumination.…”

Section: Introductionmentioning

confidence: 99%

SNIDER: Single Noisy Image Denoising and Rectification for Improving License Plate Recognition

Lee

Ahn

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

In this paper, we present an algorithm for real-world license plate recognition (LPR) from a low-quality image. Our method is built upon a framework that includes denoising and rectification, and each task is conducted by Convolutional Neural Networks. Existing denoising and rectification have been treated separately as a single network in previous research. In contrast to the previous work, we here propose an end-to-end trainable network for image recovery, Single Noisy Image DEnoising and Rectification (SNIDER), which focuses on solving both the problems jointly. It overcomes those obstacles by designing a novel network to address the denoising and rectification jointly. Moreover, we propose a way to leverage optimization with the auxiliary tasks for multi-task fitting and novel training losses. Extensive experiments on two challenging LPR datasets demonstrate the effectiveness of our proposed method in recovering the high-quality license plate image from the low-quality one and show that the the proposed method outperforms other state-of-the-art methods.

show abstract

Neural Network Encapsulation

Guo

Dai

et al. 2018

Computer Vision – ECCV 2018

View full text Add to dashboard Cite

A capsule is a collection of neurons which represents different variants of a pattern in the network. The routing scheme ensures only certain capsules which resemble lower counterparts in the higher layer should be activated. However, the computational complexity becomes a bottleneck for scaling up to larger networks, as lower capsules need to correspond to each and every higher capsule. To resolve this limitation, we approximate the routing process with two branches: a master branch which collects primary information from its direct contact in the lower layer and an aide branch that replenishes master based on pattern variants encoded in other lower capsules. Compared with previous iterative and unsupervised routing scheme, these two branches are communicated in a fast, supervised and one-time pass fashion. The complexity and runtime of the model are therefore decreased by a large margin. Motivated by the routing to make higher capsule have agreement with lower capsule, we extend the mechanism as a compensation for the rapid loss of information in nearby layers. We devise a feedback agreement unit to send back higher capsules as feedback. It could be regarded as an additional regularization to the network. The feedback agreement is achieved by comparing the optimal transport divergence between two distributions (lower and higher capsules). Such an add-on witnesses a unanimous gain in both capsule and vanilla networks. Our proposed En-capNet performs favorably better against previous state-of-the-arts on CIFAR10/100, SVHN and a subset of ImageNet.

show abstract

Reading car license plates using deep neural networks

Cited by 160 publications

References 42 publications

The impact of knowledge management, learning and socio-cultural factors on innovation

The impact of knowledge management, learning and socio-cultural factors on innovation

SNIDER: Single Noisy Image Denoising and Rectification for Improving License Plate Recognition

Neural Network Encapsulation

Contact Info

Product

Resources

About