Comparative study of feature extraction and classification methods for recognition of characters taken from vehicle registration plates

ABSTRACT

General Optical Character Recognition system works on the base of several successive steps such as pre-processing, segmentation, feature extraction, classification and post-processing. Feature extraction plays here a major role. In this article, we present an overview and comparison of various methods and approaches for off-line recognition of machine written Latin characters. We assume that individual characters are already segmented in an image. To recognize characters and translate them to text requires that each character must be described by a feature vector, which is then classified into one of the 36 classes corresponding to the uppercase Latin alphabet letters and numbers.

KEYWORDS:

• Optical character recognition
• feature extraction
• feature vector
• statistical and structural features
• template matching
• Chebyshev moments
• classification
• neural networks

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes on contributors

Ladislav Karrach received M.Sc. degree from University of Žilina, Žilina, Slovakia. He is presently a PhD. student at Technical University in Zvolen, Zvolen, Slovakia and is employed as an IT specialist in State Mint Kremnica, Slovakia. His research areas include 2D matrix code recognition and optical character recognition. He has published 6 research papers in various international journals and conferences and reviewed papers for reputed Journals.

Assoc. Prof. Elena Pivarčiová, PhD. is employed at the Technical University in Zvolen. Her research areas include applied informatics, programming and process control, application of holographic interferometry in selected technical disciplines, application of biometric methods, and image processing. She actively and continuously presents the results of research activities at scientific conferences and publishes in international scientific journals. She is the author of 4 scientific monographs, 3 university textbooks, 7 articles in the CCC journals, and 13 scientific papers published in the journals in WoS/Scopus databases.