A cascade detector for text detection in natural scene images

In this paper, we present a text detection and localization method. Our detection technique is based on a cascade of boosted ensemble and localizer uses standard image processing techniques. We propose a small set of features (39 in total) capable of detecting various type of text in grey level natural scene images. Two weak learners, linear discriminant function and log likelihood-ratio test under gaussian assumption, are evaluated. Single features and combination of features are used to form weak classifiers. The proposed scheme is evaluated on ICDAR 2003 robust reading and text locating database. The results are encouraging and the detector can process an images of 640 times 480 pixels in less than 2 seconds.

[1]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[2]  Langis Gagnon,et al.  Key-text spotting in documentary videos using Adaboost , 2006, Electronic Imaging.

[3]  Fatih Murat Porikli,et al.  Integral histogram: a fast way to extract histograms in Cartesian spaces , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Alan L. Yuille,et al.  Detecting and reading text in natural scenes , 2004, CVPR 2004.

[5]  S.M. Lucas,et al.  ICDAR 2005 text locating competition results , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[6]  Xilin Chen,et al.  Automatic detection and recognition of signs from natural scenes , 2004, IEEE Transactions on Image Processing.

[7]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8]  Nobuo Ezaki,et al.  Text detection from natural scene images: towards a system for visually impaired persons , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[9]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[10]  Dingxing Wang,et al.  Boosting image classification with LDA-based feature combination for digital photograph management , 2005, Pattern Recognit..