Home > Research > Publications & Outputs > Vehicle plate recognition using improved neocog...
View graph of relations

Vehicle plate recognition using improved neocognitron neural network

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Vehicle plate recognition using improved neocognitron neural network. / Kangin, Dmitry; Kolev, Georgi; Angelov, Plamen.
Artificial Neural Networks and Machine Learning – ICANN 2013: 23rd International Conference on Artificial Neural Networks Sofia, Bulgaria, September 10-13, 2013. Proceedings. ed. / Valeri Mladenov; Petia Koprinkova-Hristova; Günther Palm; Alessandro E. P. Villa; Bruno Appollini; Nikola Kasabov. Berlin: Springer Verlag, 2013. p. 628-640 (Lecture Notes in Computer Science; Vol. 8131).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Kangin, D, Kolev, G & Angelov, P 2013, Vehicle plate recognition using improved neocognitron neural network. in V Mladenov, P Koprinkova-Hristova, G Palm, AEP Villa, B Appollini & N Kasabov (eds), Artificial Neural Networks and Machine Learning – ICANN 2013: 23rd International Conference on Artificial Neural Networks Sofia, Bulgaria, September 10-13, 2013. Proceedings. Lecture Notes in Computer Science, vol. 8131, Springer Verlag, Berlin, pp. 628-640. https://doi.org/10.1007/978-3-642-40728-4_78

APA

Kangin, D., Kolev, G., & Angelov, P. (2013). Vehicle plate recognition using improved neocognitron neural network. In V. Mladenov, P. Koprinkova-Hristova, G. Palm, A. E. P. Villa, B. Appollini, & N. Kasabov (Eds.), Artificial Neural Networks and Machine Learning – ICANN 2013: 23rd International Conference on Artificial Neural Networks Sofia, Bulgaria, September 10-13, 2013. Proceedings (pp. 628-640). (Lecture Notes in Computer Science; Vol. 8131). Springer Verlag. https://doi.org/10.1007/978-3-642-40728-4_78

Vancouver

Kangin D, Kolev G, Angelov P. Vehicle plate recognition using improved neocognitron neural network. In Mladenov V, Koprinkova-Hristova P, Palm G, Villa AEP, Appollini B, Kasabov N, editors, Artificial Neural Networks and Machine Learning – ICANN 2013: 23rd International Conference on Artificial Neural Networks Sofia, Bulgaria, September 10-13, 2013. Proceedings. Berlin: Springer Verlag. 2013. p. 628-640. (Lecture Notes in Computer Science). doi: 10.1007/978-3-642-40728-4_78

Author

Kangin, Dmitry ; Kolev, Georgi ; Angelov, Plamen. / Vehicle plate recognition using improved neocognitron neural network. Artificial Neural Networks and Machine Learning – ICANN 2013: 23rd International Conference on Artificial Neural Networks Sofia, Bulgaria, September 10-13, 2013. Proceedings. editor / Valeri Mladenov ; Petia Koprinkova-Hristova ; Günther Palm ; Alessandro E. P. Villa ; Bruno Appollini ; Nikola Kasabov. Berlin : Springer Verlag, 2013. pp. 628-640 (Lecture Notes in Computer Science).

Bibtex

@inproceedings{71dffda6c531416aa0d9820e0a4250b9,
title = "Vehicle plate recognition using improved neocognitron neural network",
abstract = "This paper describes a novel vehicle plate recognition algorithm based on text detection and improved neocognitron neural network, similar to [1] and based on Fukushima{\textquoteright}s neocognitron. The proposed recognition algorithm allows us to improve the recognition speed and accuracy comparing to both traditional neocognitron and some state-of-art algorithms (multilayer perceptron, topological methods). It can be used as a solution for image classification and analysis tasks. As an example, the neocognitron can be utilized for symbols recognition [2]. We propose several modifications comparing to the Fukushima{\textquoteright}s modification of the neocognitron: namely, layer dimensions adjustment, threshold function and connection Gaussian kernel parameters estimation. The patterns{\textquoteright} width and height are taken into account independently in order to improve the recognition of patterns of slightly different dimensions. The learning and recognition calculations are performed as FFT convolutions in order to overcome the complexity of the neocognitron output calculations. The algorithm was tested on low-resolution (360 ×288) video sequences and gave more accurate results comparing to the state-of-the-art methods for low-resolution test set.",
keywords = "vehicle plates recognition , image segmentation, Chan-Vese algorithm , neocognitron neural network",
author = "Dmitry Kangin and Georgi Kolev and Plamen Angelov",
year = "2013",
doi = "10.1007/978-3-642-40728-4_78",
language = "English",
isbn = "9783642407277",
series = "Lecture Notes in Computer Science",
publisher = "Springer Verlag",
pages = "628--640",
editor = "Valeri Mladenov and Petia Koprinkova-Hristova and Palm, {G{\"u}nther } and Villa, {Alessandro E. P.} and Bruno Appollini and Nikola Kasabov",
booktitle = "Artificial Neural Networks and Machine Learning – ICANN 2013",

}

RIS

TY - GEN

T1 - Vehicle plate recognition using improved neocognitron neural network

AU - Kangin, Dmitry

AU - Kolev, Georgi

AU - Angelov, Plamen

PY - 2013

Y1 - 2013

N2 - This paper describes a novel vehicle plate recognition algorithm based on text detection and improved neocognitron neural network, similar to [1] and based on Fukushima’s neocognitron. The proposed recognition algorithm allows us to improve the recognition speed and accuracy comparing to both traditional neocognitron and some state-of-art algorithms (multilayer perceptron, topological methods). It can be used as a solution for image classification and analysis tasks. As an example, the neocognitron can be utilized for symbols recognition [2]. We propose several modifications comparing to the Fukushima’s modification of the neocognitron: namely, layer dimensions adjustment, threshold function and connection Gaussian kernel parameters estimation. The patterns’ width and height are taken into account independently in order to improve the recognition of patterns of slightly different dimensions. The learning and recognition calculations are performed as FFT convolutions in order to overcome the complexity of the neocognitron output calculations. The algorithm was tested on low-resolution (360 ×288) video sequences and gave more accurate results comparing to the state-of-the-art methods for low-resolution test set.

AB - This paper describes a novel vehicle plate recognition algorithm based on text detection and improved neocognitron neural network, similar to [1] and based on Fukushima’s neocognitron. The proposed recognition algorithm allows us to improve the recognition speed and accuracy comparing to both traditional neocognitron and some state-of-art algorithms (multilayer perceptron, topological methods). It can be used as a solution for image classification and analysis tasks. As an example, the neocognitron can be utilized for symbols recognition [2]. We propose several modifications comparing to the Fukushima’s modification of the neocognitron: namely, layer dimensions adjustment, threshold function and connection Gaussian kernel parameters estimation. The patterns’ width and height are taken into account independently in order to improve the recognition of patterns of slightly different dimensions. The learning and recognition calculations are performed as FFT convolutions in order to overcome the complexity of the neocognitron output calculations. The algorithm was tested on low-resolution (360 ×288) video sequences and gave more accurate results comparing to the state-of-the-art methods for low-resolution test set.

KW - vehicle plates recognition

KW - image segmentation

KW - Chan-Vese algorithm

KW - neocognitron neural network

U2 - 10.1007/978-3-642-40728-4_78

DO - 10.1007/978-3-642-40728-4_78

M3 - Conference contribution/Paper

SN - 9783642407277

T3 - Lecture Notes in Computer Science

SP - 628

EP - 640

BT - Artificial Neural Networks and Machine Learning – ICANN 2013

A2 - Mladenov, Valeri

A2 - Koprinkova-Hristova, Petia

A2 - Palm, Günther

A2 - Villa, Alessandro E. P.

A2 - Appollini, Bruno

A2 - Kasabov, Nikola

PB - Springer Verlag

CY - Berlin

ER -