Multilingual Artificial Text Detection Using a Cascade of Transforms
- 1 August 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 309-313
- https://doi.org/10.1109/icdar.2013.69
Abstract
This paper presents a method for multilingual artificial text detection and extraction from still images. The proposed detection scheme relies on a cascade of spatial transforms followed by a box counting based fractal dimension approach to exploit the self-similar redundancy of patterns in the shapes of characters in the text. The detected text regions are validated using GLCM based features and are segmented from the background using the proposed binarization scheme. The proposed method is evaluated on five data sets containing textual occurrences in Urdu, English, Chinese, Arabic and Hindi. The experimental results realized show very promising precision and recall rates which are also consistent across different data sets.Keywords
This publication has 23 references indexed in Scilit:
- Text detection for video analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Robust multifont OCR system from gray level imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Text segmentation using linear transformsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Morphological text extraction from imagesIEEE Transactions on Image Processing, 2000
- Automatic text detection and tracking in digital videoIEEE Transactions on Image Processing, 2000
- Textfinder: an automatic system to detect and recognize text in imagesIeee Transactions On Pattern Analysis and Machine Intelligence, 1999
- A video text extraction method for character recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Efficient Automatic Text Location Method and Content-Based Indexing and Structuring of Video DatabaseJournal of Visual Communication and Image Representation, 1996
- Locating text in complex color imagesPattern Recognition, 1995
- A theory for multiresolution signal decomposition: the wavelet representationIeee Transactions On Pattern Analysis and Machine Intelligence, 1989