A novel design for vehicle license plate detection and recognition

Vehicles on the road are rising in extensive numbers, particularly in proportion to the industrial revolution and growing economy. The significant use of vehicles has increased the probability of traffic rules violation, causing unexpected accidents, and triggering traffic crimes. In order to overcome these problems, an intelligent traffic monitoring system is required. The intelligent system can play a vital role in traffic control through the number plate detection of the vehicles. In this research work, a system is developed for detecting and recognizing of vehicle number plates using a convolutional neural network (CNN), a deep learning technique. This system comprises of two parts: number plate detection and number plate recognition. In the detection part, a vehicle’s image is captured through a digital camera. Then the system segments the number plate region from the image frame. After extracting the number plate region, a super resolution method is applied to convert the low-resolution image into a high-resolution image. The super resolution technique is used with the convolutional layer of CNN to reconstruct the pixel quality of the input image. Each character of the number plate is segmented using a bounding box method. In the recognition part, features are extracted and classified using the CNN technique. The novelty of this research is the development of an intelligent system employing CNN to recognize number plates, which have less resolution, and are written in the Bengali language.

show abstract

“…Prabhakar et al [6] proposed a webcam for capturing images. This system can localize several sizes of number plates from the captured images.…”

Section: Related Workmentioning

confidence: 99%

Intelligent System for Vehicles Number Plate Detection and Recognition Using Convolutional Neural Networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Um dos problemas deste métodoé que gera uma grande quantidade de falsos positivos, precisando assim, de um classificador para minimizá-los. Neto et al (2015) e Prabhakar and Anupama (2014) baseiam seus métodos na utilização da transformada de Hough (Duda and Hart, 1972) para detectar linhas horizontais e verticais dentro da imagem com o objetivo de segmentar a placa, porém a transformada falha quando se apresentam bordas pouco definidas dentro da imagem. Já o trabalho proposto por Elbamby et al (2016) emprega o operador Sobel (Sobel, 1990) combinado com a análise de componentes conectados (CCA, connected component analysis) para encontrar as bordas dentro da imagem, e assim conseguir segmentar a placa.…”

Section: Introductionunclassified

Sistema automático para reconhecimento de placas veiculares: comparação entre SVM-HOG e Deep learning

Salazar

Barbosa

Stemmer

et al. 2019

Anais Do 14º Simpósio Brasileiro De Automação Inteligente

View full text Add to dashboard Cite

In the present work, we present an approach for automatic detection and recognition of vehicular plates considering factors such as: changes of illumination in the images, low contrast, noise, and different acquisition perspectives. For plate detection, a filter based on mathematical morphological operations is applied, followed by a combination of morphologicalgeometric operations and two classification approaches based on SVM-HOG and the CNN Inception ResNet v2 architecture. Then, the characters are segmented by a quality rating algorithm for the plates. Finally, the same classification approaches are used to recognize the characters. A database with images acquired on a street in the city of São Paulo was used, obtaining an overall system accuracy of 97%. Thus, its feasibility to be implemented in different intelligent transport systems applications. Resumo: No presente trabalhoé apresentada uma proposta para a detecção e reconhecimento automático de placas veiculares considerando fatores como: mudanças de iluminação nas imagens, baixo contraste, ruido e diferentes perspectivas de aquisição. Para a detecção da placa,é aplicado um filtro baseado em operações morfológicas matemáticas, seguido de uma combinação de operações morfológicas-geométricas e duas abordagens de classificação baseadas em SVM-HOG e a arquitetura CNN Inception ResNet v2. Depois, segmenta-se os caracteres através de um algoritmo de classificaçao de qualidade das placas. Por ultimo, são utilizadas as mesmas abordagens de classificação para reconhecer os caracteres. Foi usado um banco de dados com imagens adquiridas em uma rua da cidade de São Paulo, Obtendo uma acurácia global do sistema de 97%. Mostrando assim, sua viabilidade para ser implementado em diferentes aplicações de sistemas inteligentes de transporte.

show abstract

“…The border of the license plate is detected as a rectangular by the edge detector as the color vicissitudes between the license plate character and its background [7]. Besides, there are also several works by combining the edge feature with other schemes [8][9][10][11]. They are fast and simple.…”

Section: Introductionmentioning

confidence: 99%

Fast Cartoon-Texture Decomposition Filtering Based License Plate Detection Method

Wang

Zhao

Liu

et al. 2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Vehicle license plate detection is an important step in automatic license plate recognition, which is prone to be influenced by the background interference and complex environment conditions. It is known that cartoon-texture decomposition split an image into geometric cartoon and texture component, which can remove background interference away from the vehicle image. In this paper, we introduce a fast cartoon-texture decomposition filter into the detection process. Combining the edge detection, morphological filtering and Radon transform based tilt correction method, we formulate a new license plate detection algorithm. Experiment results confirm that the proposed algorithm can remove background interference away, inhibit the emergence of fake license plates, and improve the detection accuracy. Moreover, there is no inner loop iteration in the new algorithm, so it is fast and high-efficiency.

show abstract

A novel design for vehicle license plate detection and recognition

Cited by 20 publications

References 6 publications

Intelligent System for Vehicles Number Plate Detection and Recognition Using Convolutional Neural Networks

Intelligent System for Vehicles Number Plate Detection and Recognition Using Convolutional Neural Networks

Sistema automático para reconhecimento de placas veiculares: comparação entre SVM-HOG e Deep learning

Fast Cartoon-Texture Decomposition Filtering Based License Plate Detection Method

Contact Info

Product

Resources

About