License Plate Character Recognition Research Based on Shape Context

Sun, Yong; Lan, Shanzhen; Li, Shaobin

doi:10.1109/imccc.2014.106

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For local shape information for each point context that was ignored in the LTN algorithm, the paper introduces the concept of Shape Context (SCLTN) [24][25][26][27][28] in LTN, which allows for the determination of correspondence between each data point in the periodic sequence. The shape context is a description for the shape, whose main purpose is to capture the relative position of each data point in space to achieve a stricter and more accurate match between points, as shown in Figure 5.…”

Section: Typical Period Extractionmentioning

confidence: 99%

Gait Recognition of Acceleration Sensor for Smart Phone Based on Multiple Classifier Fusion

Huan

Chen

et al. 2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Gait, as a kind of biological feature, has a profound value in personnel identification. This paper analyzes gait characteristics based on acceleration sensors of smart phones and proposes a new gait recognition method. First, in view of the existing methods in the process of extraction of gait features, a large number of redundant calculations, cycle detection error, and the phase deviation issue during the week put forward the Shape Context (SC) and Linear Time Normalized (LTN) combining SCLTN calibration method of gait cycle sequence matching, to represent the whole extract typical gait cycle gait. In view of the existing extracted gait features are still some conventional features; the velocity change of relatively uniform acceleration and the change of acceleration per unit time are proposed as new features. Secondly, combining new features with traditional features to form a new feature is set for training alternative feature set, from which the training time and recognition effect of multiple classifiers are screened. Finally, a new multiclassifier fusion method, Multiple Scale Voting (MSV), is proposed to fuse the results of Multiple classifiers to obtain the final classification results. In order to verify the performance of the proposed method, gait data of 32 testers are collected. The final experimental results show that the new feature has good separability, and the recognition rate of fusion feature set after MSV algorithm is 98.42%.

show abstract

Section: Typical Period Extractionmentioning

confidence: 99%

Gait Recognition of Acceleration Sensor for Smart Phone Based on Multiple Classifier Fusion

Huan

Chen

et al. 2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Low quality license plate character recognized with this method [3] Sun Yuzheet.al proposed sampling based on classic shape context algorithm and simplified free man chain code. Recognition accuracy was achieved up to 92.7 % [4]. Mansour Nejatet.al described about Kirsch edge operator and image projection for featureextraction classified using mixture of experts which uses the multilayer perceptron (MLPs) as expert.…”

Section: IImentioning

confidence: 99%

“…This technique also uses to recognize the vehicles that are involved in any offenses like kidnapping etc. these all are the applications of a LPR technique [3][4][5]. To design a classifieds for the character recognition we mainly match the templates of different specifications.…”

mentioning

confidence: 99%

Character Recognition of Vehicle License Plate using Feature Extraction: A Review Paper

Dagar¹

2018

IJRASET

View full text Add to dashboard Cite

The License Plate Recognition (LPR) system is the most popular method for the mass surveillance of the automobiles now days. The LPR system is basically works into 3 steps , 1 st step is to recognize vehicle license plate and then extract numbers from that and third step is to character recognition means to read out the characters of an number plate. The LPR is also some face some difficulties due to no uniform structure of number plates and illumination is also cause some difficulties in some areas. I. INTRODUCTION From the past two decades there is an boom in the automobile industry which increase the number of vehicles on road and make the transportation faster and cheaper. Till now human are employed for monitoring and controlling the traffic related parameter which is very difficult and very complex. Thus the developed countries are now opting a intelligent transport system to monitor the traffic. The main aim to design these intelligent systems is to monitor the vehicle more accurately and to construct a applicable scheme to control the traffic [1,2]. License plate recognition system is an integral part of these intelligent transport systems, the license plate recognition techniques makes it possible to use image processing technique to extract the alphanumeric numbers from the vehicle license number plates and to read out the plate. This techniques makes possible to recognize the number plate numbers from an moving or an stationary vehicle which makes vehicle recognition more easier. This technique is employed for various kind of uses like to automatic charge the toll fees from the vehicle owner while he passing from a toll way and to recognize the vehicle who breaks the traffic rules and to recognize the drivers who breaks the traffic rules to punish them. This technique also uses to recognize the vehicles that are involved in any offenses like kidnapping etc. these all are the applications of a LPR technique [3][4][5]. To design a classifieds for the character recognition we mainly match the templates of different specifications. To match the template by a automatic method we first set some sample templates and then we obtain some character from these templates. Then the character obtained from these templates is compare with the sample templates and the template which is closely matching with the sample templates is consider as an result of character recognition. As if the license plates are standardized means there size and the font uses in character is fixed then it's become much easier to recognize the character but this process is slow and time consuming and this method is not feasible in real environment [6][7][8]. In the field of plate recognition, the most commonly used classifier is ANN [9]. To get the maximum efficient results from these neural networks we have to choose the appropriate number of hidden layers and number of neurons. Now a day's , various types of multilayer NN are being applied for the character recognition eg. RBF, Kohonen, ART etc. apart from all these types of mul...

show abstract