TextCatcher: a method to detect curved and challenging text in natural scenes
From LRDE
- Authors
- Jonathan Fabrizio, Myriam Robert-Seidowsky, Séverine Dubuisson, Stefania Calarasanu, Raphaël Boissel
- Journal
- International Journal on Document Analysis and Recognition
- Type
- article
- Publisher
- Springer
- Keywords
- Image
- Date
- 2016-04-08
Abstract
In this paper, we propose a text detection algorithm which is hybrid and multi-scale. First, it relies on a connected component-based approach: After the segmentation of the image, a classification step using a new wavelet descriptor spots the letters. A new graph modeling and its traversal procedure allow to form candidate text areas. Second, a texture-based approach discards the false positives. Finally, the detected text areas are precisely cut out and a new binarization step is introduced. The main advantage of our method is that few assumptions are put forward. Thus, ``challenging texts like multi-sizedmulti-colored, multi-oriented or curved text can be localized. The efficiency of TextCatcher has been validated on three different datasets: Two come from the ICDAR competition, and the third one contains photographs we have taken with various daily life texts. We present both qualitative and quantitative results.
Bibtex (lrde.bib)
@Article{ fabrizio.16.ijdar, author = {Jonathan Fabrizio and Myriam Robert-Seidowsky and S\'everine Dubuisson and Stefania Calarasanu and Rapha\"el Boissel}, title = {TextCatcher: a method to detect curved and challenging text in natural scenes}, journal = {International Journal on Document Analysis and Recognition}, year = 2016, volume = xx, number = x, publisher = {Springer}, pages = {1--19}, month = feb, abstract = {In this paper, we propose a text detection algorithm which is hybrid and multi-scale. First, it relies on a connected component-based approach: After the segmentation of the image, a classification step using a new wavelet descriptor spots the letters. A new graph modeling and its traversal procedure allow to form candidate text areas. Second, a texture-based approach discards the false positives. Finally, the detected text areas are precisely cut out and a new binarization step is introduced. The main advantage of our method is that few assumptions are put forward. Thus, ``challenging texts'' like multi-sized, multi-colored, multi-oriented or curved text can be localized. The efficiency of TextCatcher has been validated on three different datasets: Two come from the ICDAR competition, and the third one contains photographs we have taken with various daily life texts. We present both qualitative and quantitative results.} }