Efficient Farsi license plate recognition

Delforouzi, Ahmad; Pooyan, Mohammad

doi:10.1109/icics.2009.5397504

Cited by 9 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [1], Gaussian filter and equalization histogram used for preprocessing and global Otsu thresholding used for binarization. After using Morphological operator, connected component analysis applied to obtain plate candidate.…”

Section: Literature Reviewmentioning

confidence: 99%

Automatic license plate localization in traffic videos

Shami

Rafiee²,

Bidokhti

et al. 2014

2014 International Congress on Technology, Communication and Knowledge (ICTCK)

View full text Add to dashboard Cite

This paper addresses the problem of Iranian license plate localization in the traffic video frames. To find the location of license plates in any frame, as a new method, first we detect the moving vehicles with a background extraction algorithm. The background image must be updated in any specified period of time and subtracted from the current frame. Foreground image includes moving objects. After detecting the moving vehicles, using morphological techniques and histogram and area properties, the location of license plates are extracted. Simulation results illustrate the high accuracy of the proposed method.I.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Automatic license plate localization in traffic videos

Shami

Rafiee²,

Bidokhti

et al. 2014

2014 International Congress on Technology, Communication and Knowledge (ICTCK)

View full text Add to dashboard Cite

show abstract

“…This method however is sensitive to the license plate dimensions and is not robust enough to handle all practical conditions. A real time solution with intelligent frame selection from input video was presented in [4]. It then enhances the obtained frame using Gaussian filter and histogram equalization.…”

Section: Introductionmentioning

confidence: 99%

A Design Flow for Robust License Plate Localization and Recognition in Complex Scenes

Wazalwar¹,

Oruklu²,

Saniie³

2012

JTTs

View full text Add to dashboard Cite

In this paper, we present a new design flow for robust license plate localization and recognition. The algorithm consists of three stages: 1) license plate localization; 2) character segmentation; and 3) feature extraction and character recognition. The algorithm uses Mexican hat operator for edge detection and Euler number of a binary image for identifying the license plate region. A pre-processing step using median filter and contrast enhancement is employed to improve the character segmentation performance in case of low resolution and blur images. A unique feature vector comprised of region properties, projection data and reflection symmetry coefficient has been proposed. Back propagation artificial neural network classifier has been used to train and test the neural network based on the extracted feature. A thorough testing of algorithm is performed on a database with varying test cases in terms of illumination and different plate conditions. Practical considerations like existence of another text block in an image, presence of dirt or shadow on or near license plate region, license plate with rows of characters and sensitivity to license plate dimensions have been addressed. The results are encouraging with success rate of 98.10% for license plate localization and 97.05% for character recognition

show abstract

“…License plate location in images due to having many characters and their repeating in sequence usually contains a higher histogram than other areas [12]. Using the histogram analysis is not a suitable criterion and there is this probability that there are other areas similar to it [5]. In [6], a six-layer cascaded classifier is constructed to increase the detection speed, in which the first two layers are based on global features and the last four layers are based on local Haar-like features.…”

Section: Introductionmentioning

confidence: 99%

“…It is usually used a three layers neural network to do it. The first layer is used as input layer, second layer as hidden layer and the third layer as the output layer [5]. In such methods the input layer includes a collection of license plate features.…”

Section: Introductionmentioning

confidence: 99%

A New Method for Positioning Persian License Plates

Rahmanian¹,

Javidan²,

Keshtgary³

2011

IJET

View full text Add to dashboard Cite

Abstract-Today the necessity of using smart systems which are able to diagnose the cars plague correctly from pictures is felt more than ever by expanding the number of vehicles. In License Plate Recognition systems, detecting plaque location is considered the most important phase so that the correct rate of it, will affect all subsequent phases. There are different images with different resolutions and sever changes in the size of images which taken through being far or near to the camera, it makes many existing methods face problems or longer processing. In this paper a new method is suggested based on simulation concepts which used in spectra analysis for accurate and fast position detection by using edge concepts and morphological operators in image processing. The suggested method is a compound method and fast enough and it extracts the plague location from vehicle image correctly. The algorithm is implemented in MATLAB and the results obtained agreed with theoretical predictions. The proposed method has 93.3 % of correct detection rate and 150 ms of processing time.

show abstract

Efficient Farsi license plate recognition

Cited by 9 publications

References 8 publications

Automatic license plate localization in traffic videos

Automatic license plate localization in traffic videos

A Design Flow for Robust License Plate Localization and Recognition in Complex Scenes

A New Method for Positioning Persian License Plates

Contact Info

Product

Resources

About