Scene text extraction in natural scene images using hierarchical feature combining and verification
Authors:
- Y.J. SongYSY.J. Song
- Y.W. ChoiYCY.W. Choi
- S.Y. ChiSCS.Y. Chi
- K.K. KimKKK.K. Kim
- Y.K. ChungYCY.K. Chung
- 1 January 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (10514651) , 679-682 Vol.2
Abstract
We propose a method that extracts text regions in natural scene images using low-level image features and that verifies the extracted regions through a high-level text stroke feature. Then the two level features are combined hierarchically. The low-level features are color continuity, gray-level variation and color variance. The color continuity is used since most of the characters in a text region have the same color, and the gray-level variation is used since the text strokes are distinctive to the background in their gray-level values. Also, the color variance is used since the text strokes are distinctive in their colors to the background, and this value is more sensitive than the gray-level variations. As a high level feature, text stroke is examined using multi-resolution wavelet transforms on local image areas and the feature vector is input to a SVM (support vector machine) for verification. We tested the proposed method with various kinds of the natural scene images and confirmed that extraction rates are high even in complex images.Keywords
This publication has 6 references indexed in Scilit:
- Automatic caption localization in compressed videoIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Automatic text detection and tracking in digital videoIEEE Transactions on Image Processing, 2000
- AUTOMATIC TEXT LOCATION IN IMAGES AND VIDEO FRAMESPattern Recognition, 1998
- Locating text in complex color imagesPattern Recognition, 1995
- Support-vector networksMachine Learning, 1995
- Recognizing characters in scene imagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994