A High Performance Algorithm of Vehicle Plate Location and Recognition in Intelligent Transportation

2012 ◽  
Vol 253-255 ◽  
pp. 1443-1452
Author(s):  
Wan Jun Liu ◽  
Zhan Zhang ◽  
Wen Tao Jiang ◽  
Heng Yuan
Keyword(s):  
Neural Network ◽  
Character Recognition ◽  
High Performance ◽  
Intelligent Transportation System ◽  
Intelligent Transportation ◽  
License Plate ◽  
Search Area ◽  
System A ◽  
Weight Value ◽  
Plate Location

For the problem of slow plate location, the low accuracy of information identifying in the intelligent transportation system, a new algorithm of vehicle plate location and character recognition with high performance is presented in this paper. Firstly, the vehicle plate image is pre-processed, and then search for the edge of rapidly protruding rectangular, collect the similar trend of bilateral curve in the search area of rectangular, then selected the area with outstanding bilateral similar characteristics, so locate the true license plate which contains characters. Finally, match with the bit weight value of the multi-template by the improving neural network model, and identify the characters. The proposed algorithm focuses on the rectangular features of license plates and the important features of parallel bilateral with character, to the use of algorithm with the new parallel ectopic template removed improved the speed of vehicle plate location and the accuracy of character recognition.

Research of License Plate Recognition System Based on Labview

2015 ◽  
Vol 734 ◽  
pp. 646-649
Author(s):  
Zhong Hua Hu ◽  
Chen Tang
Keyword(s):  
Virtual Instrument ◽  
Character Recognition ◽  
Traffic Management ◽  
Intelligent Transportation System ◽  
Recognition System ◽  
License Plate ◽  
Morphological Operations ◽  
License Plate Recognition ◽  
Plate Location ◽  
Traffic Management System

The vehicle license plate recognition system is the intelligent traffic management system based on the image and the character recognition technology, which is an important part of the intelligent transportation system. This paper introduces a method of vehicle license plate location based on edge detection and morphological operations, virtual instrument is combined with machine vision of the license plate recognition method [1]. Finally the license plate number of the vehicle is get. Experiment results show that such method can simplify the algorithm and has some correct location rate.

An Efficient Algorithm for License Plate Recognition

2013 ◽  
Vol 278-280 ◽  
pp. 1297-1300
Author(s):  
Zhong Yan Liu ◽  
Jian Yang ◽  
Hong Mei Nie
Keyword(s):  
Character Recognition ◽  
Intelligent Transportation System ◽  
Character Segmentation ◽  
Experimental Result ◽  
License Plate ◽  
License Plate Recognition ◽  
License Plate Location ◽  
Whole Process ◽  
Result Show ◽  
Plate Location

The license plate recognition(LPR) is the key technology in intelligent transportation system. This paper discusses the whole process of license plate recognition technology, include the license plate image preprocessing, license plate location, character segmentation and character recognition, and simulated it by MATLAB. The experimental result show this method can obtain good recognition effect.

Research on Identification Technology of Vehicle License Plate Based on Image Processing

2014 ◽  
Vol 513-517 ◽  
pp. 2827-2830
Author(s):  
Gui Ming Shi ◽  
Tong Wu ◽  
Hang Su ◽  
Qing Tao Wei
Keyword(s):  
Image Processing ◽  
Character Recognition ◽  
Template Matching ◽  
Intelligent Transportation System ◽  
Transport Systems ◽  
License Plate ◽  
License Plate Recognition ◽  
Tilt Correction ◽  
License Plate Location ◽  
Plate Location

Automatic vehicle license plate is an important part of intelligent transportation system. The success of the plate recognition will have a deep impact on the construction of intelligent transport systems. Image processing, tilt correction, character delimitation, character recognition and matching are main applications of vehicle license plate recognition, and the above process are implemented in matlab environment. Vehicle license plate location is implemented by vehicle license plate locating method based on edge detection and morphology filter in this article. The tilt correction mode based on Hough transform is used for license plate tilt correction section; character delimitation algorithm is used for character delimitation to achieve the vehicle license plate character segmentation; character recognition method based on template matching is chosen for character recognition section in this article, and successfully identify the license plate number.

Application of Image Processing to the Vehicle License Plate Recognition

2013 ◽  
Vol 760-762 ◽  
pp. 1638-1641 ◽  
Author(s):  
Chun Yu Chen ◽  
Bao Zhi Cheng ◽  
Xin Chen ◽  
Fu Cheng Wang ◽  
Chen Zhang
Keyword(s):  
Traffic Engineering ◽  
Character Recognition ◽  
Character Segmentation ◽  
License Plate ◽  
License Plate Recognition ◽  
Edge Extraction ◽  
Recognition Method ◽  
License Plate Location ◽  
Vehicle License Plate Recognition ◽  
Plate Location

At present, the traffic engineering and automation have developed, and the vehicle license plate recognition technology need get a corresponding improvement also. In case of identifying a car license picture, the principle of automatic license plate recognition is illustrated in this paper, and the processing is described in detail which includes the pre-processing, the edge extraction, the license plate location, the character segmentation, the character recognition. The program implementing recognition is edited by Matlab. The example result shows that the recognition method is feasible, and it can be put into practice.

scholarly journals License Plate Location and Recognition on Neural Network

2020 ◽  
Vol 1642 ◽  
pp. 012012
Author(s):  
Zhilong He ◽  
Zhongjun Xiao ◽  
Zhiguo Yan
Keyword(s):  
Neural Network ◽  
License Plate ◽  
License Plate Location ◽  
Plate Location

License Plate Location Method Based on LOG Edge Detection Operator

2011 ◽  
Vol 108 ◽  
pp. 52-55 ◽  
Author(s):  
Zhan Wen Wu
Keyword(s):  
Recognition System ◽  
License Plate ◽  
License Plate Recognition ◽  
Block Method ◽  
Key Technology ◽  
Location Method ◽  
License Plate Location ◽  
Color Plate ◽  
Search Area ◽  
Plate Location

The license plate location method is the key technology of license plate recognition system, new algorithm is proposed based on LOG operator detecting edge of License Plate Location. First, a large number of color plate images are preprocessed to remove the background interference information, and then rough location of license plate based on block method, search area of plate will be greatly reduced and accurate positioning the plate will be realized by LOG operator combined with projection method. Static license plate image positioning by simulation and analysis show that the method has high accuracy in license plate location.

scholarly journals BengaliNet: A Low-Cost Novel Convolutional Neural Network for Bengali Handwritten Characters Recognition

2021 ◽  
Vol 11 (15) ◽  
pp. 6845
Author(s):  
Abu Sayeed ◽  
Jungpil Shin ◽  
Md. Al Mehedi Hasan ◽  
Azmain Yakin Srizon ◽  
Md. Mehedi Hasan
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Character Recognition ◽  
High Performance ◽  
Low Cost ◽  
Traditional Learning ◽  
Neural Network Architecture ◽  
Handwritten Character Recognition ◽  
Handwritten Character

As it is the seventh most-spoken language and fifth most-spoken native language in the world, the domain of Bengali handwritten character recognition has fascinated researchers for decades. Although other popular languages i.e., English, Chinese, Hindi, Spanish, etc. have received many contributions in the area of handwritten character recognition, Bengali has not received many noteworthy contributions in this domain because of the complex curvatures and similar writing fashions of Bengali characters. Previously, studies were conducted by using different approaches based on traditional learning, and deep learning. In this research, we proposed a low-cost novel convolutional neural network architecture for the recognition of Bengali characters with only 2.24 to 2.43 million parameters based on the number of output classes. We considered 8 different formations of CMATERdb datasets based on previous studies for the training phase. With experimental analysis, we showed that our proposed system outperformed previous works by a noteworthy margin for all 8 datasets. Moreover, we tested our trained models on other available Bengali characters datasets such as Ekush, BanglaLekha, and NumtaDB datasets. Our proposed architecture achieved 96–99% overall accuracies for these datasets as well. We believe our contributions will be beneficial for developing an automated high-performance recognition tool for Bengali handwritten characters.

scholarly journals Algorithm for auto annotation of scanned documents based on subregion tiling and shallow networks

2021 ◽  
Author(s):  
Komuravelli Prashanth ◽  
Kalidas Yeturu
Keyword(s):  
Neural Network ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
High Performance ◽  
Performance Metrics ◽  
Training Data ◽  
Mean Average Precision ◽  
Average Precision ◽  
Squared Error Loss Function ◽  
Scanned Documents

<div>There are millions of scanned documents worldwide in around 4 thousand languages. Searching for information in a scanned document requires a text layer to be available and indexed. Preparation of a text layer requires recognition of character and sub-region patterns and associating with a human interpretation. Developing an optical character recognition (OCR) system for each and every language is a very difficult task if not impossible. There is a strong need for systems that add on top of the existing OCR technologies by learning from them and unifying disparate multitude of many a system. In this regard, we propose an algorithm that leverages the fact that we are dealing with scanned documents of handwritten text regions from across diverse domains and language settings. We observe that the text regions have consistent bounding box sizes and any large font or tiny font scenarios can be handled in preprocessing or postprocessing phases. The image subregions are smaller in size in scanned text documents compared to subregions formed by common objects in general purpose images. We propose and validate the hypothesis that a much simpler convolution neural network (CNN) having very few layers and less number of filters can be used for detecting individual subregion classes. For detection of several hundreds of classes, multiple such simpler models can be pooled to operate simultaneously on a document. The advantage of going by pools of subregion specific models is the ability to deal with incremental addition of hundreds of newer classes over time, without disturbing the previous models in the continual learning scenario. Such an approach has distinctive advantage over using a single monolithic model where subregions classes share and interfere via a bulky common neural network. We report here an efficient algorithm for building a subregion specific lightweight CNN models. The training data for the CNN proposed, requires engineering synthetic data points that consider both pattern of interest and non-patterns as well. We propose and validate the hypothesis that an image canvas in which optimal amount of pattern and non-pattern can be formulated using a means squared error loss function to influence filter for training from the data. The CNN hence trained has the capability to identify the character-object in presence of several other objects on a generalized test image of a scanned document. In this setting some of the key observations are in a CNN, learning a filter depends not only on the abundance of patterns of interest but also on the presence of a non-pattern context. Our experiments have led to some of the key observations - (i) a pattern cannot be over-expressed in isolation, (ii) a pattern cannot be under-xpressed as well, (iii) a non-pattern can be of salt and pepper type noise and finally (iv) it is sufficient to provide a non-pattern context to a modest representation of a pattern to result in strong individual sub-region class models. We have carried out studies and reported \textit{mean average precision} scores on various data sets including (1) MNIST digits(95.77), (2) E-MNIST capital alphabet(81.26), (3) EMNIST small alphabet(73.32) (4) Kannada digits(95.77), (5) Kannada letters(90.34), (6) Devanagari letters(100) (7) Telugu words(93.20) (8) Devanagari words(93.20) and also on medical prescriptions and observed high-performance metrics of mean average precision over 90%. The algorithm serves as a kernel in the automatic annotation of digital documents in diverse scenarios such as annotation of ancient manuscripts and hand-written health records.</div>

Sign in / Sign up

Export Citation Format

Share Document