Toward Integrated Scene Text Reading

The growth in digital camera usage combined with a worldly abundance of text has translated to a rich new era for a classic problem of pattern recognition, reading. While traditional document processing often faces challenges such as unusual fonts, noise, and unconstrained lexicons, scene text readi...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2014-02, Vol.36 (2), p.375-387
Main Authors: Weinman, Jerod J., Butler, Zachary, Knoll, Dugan, Feild, Jacqueline
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Artificial Intelligence
baseline estimation
Character recognition
Computer science
control theory
systems
cropped word recognition
Data Interpretation, Statistical
discriminative semi-Markov model
Documentation - methods
Exact sciences and technology
Hidden Markov models
image binarization
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image segmentation
Natural Language Processing
Noise
Pattern Recognition, Automated - methods
Pattern recognition. Digital image processing. Computational geometry
Probabilistic logic
Reproducibility of Results
Robustness
Scene text recognition
Sensitivity and Specificity
skew detection
Speech and sound recognition and synthesis. Linguistics
Systems Integration
text guidelines
Text recognition
word normalization
word segmentation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The growth in digital camera usage combined with a worldly abundance of text has translated to a rich new era for a classic problem of pattern recognition, reading. While traditional document processing often faces challenges such as unusual fonts, noise, and unconstrained lexicons, scene text reading amplifies these challenges and introduces new ones such as motion blur, curved layouts, perspective projection, and occlusion among others. Reading scene text is a complex problem involving many details that must be handled effectively for robust, accurate results. In this work, we describe and evaluate a reading system that combines several pieces, using probabilistic methods for coarsely binarizing a given text region, identifying baselines, and jointly performing word and character segmentation during the recognition process. By using scene context to recognize several words together in a line of text, our system gives state-of-the-art performance on three difficult benchmark data sets.
ISSN:0162-8828
1939-3539
2160-9292
DOI:10.1109/TPAMI.2013.126