HMM-Based Multi Oriented Text Recognition in Natural Scene Image

Recognition of curved text in natural scene image is a challenging task. Due to complex background and unpredictable characteristics of scene text and noise, text characters in strings are often touching that affects the performance of segmentation and recognition. This paper presents a novel approa...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings - IEEE Computer Society Conference on Pattern Recognition and Image Processing S. 288 - 292
Hauptverfasser: Roy, Sangheeta, Roy, Partha Pratim, Shivakumara, Palaiahnakote, Louloudis, Georgios, Tan, Chew Lim, Pal, Umapada
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.11.2013
Schlagworte:
Binarization
Character recognition
Curved Text Recognition
Feature extraction
Hidden Markov Model
Hidden Markov models
Image recognition
Image segmentation
Optical character recognition software
Scene Text Recognition
Text recognition
ISSN:0730-6512
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Recognition of curved text in natural scene image is a challenging task. Due to complex background and unpredictable characteristics of scene text and noise, text characters in strings are often touching that affects the performance of segmentation and recognition. This paper presents a novel approach for curved text recognition using Hidden Markov Models (HMM). From curved text, a path of sliding window is estimated and features extracted from the sliding window are fed to the HMM system for recognition. We evaluate two frame-wise feature extraction algorithms namely Marti-Bunk and local gradient histogram. The proposed approach has been tested on different natural scene benchmark as well as video databases, e.g. ICDAR-2003competition scene images, MSRA-TD500 and NUS. We have achieved word recognition accuracy of about 63.28%, 58.41% and 53.62%y for horizontal text, non-horizontal text and curved text, respectively.
ISSN:0730-6512
DOI:10.1109/ACPR.2013.60