Text Localization and Extraction from Complex Gray Images
We propose two texture-based approaches, one involving Gabor filters and the other employing log-polar wavelets, for separating text from non-text elements in a document image. Both the proposed algorithms compute local energy at some information-rich points, which are marked by Harris’ corner detector. The advantage of this approach is that the algorithm calculates the local energy at selected points and not throughout the image, thus saving a lot of computational time. The algorithm has been tested on a large set of scanned text pages and the results have been seen to be better than the results from the existing algorithms. Among the proposed schemes, the Gabor filter based scheme marginally outperforms the wavelet based scheme.
KeywordsCorner Point Delaunay Triangulation Document Image Gabor Filter Text Region
Unable to display preview. Download preview PDF.
- 2.Smith, M.A., Kanade, T.: Video skimming for quick browsing based on audio and image characterization, CMU-CS-95-186, Technical report, Carnegie Mellon University (1995)Google Scholar
- 4.Wu, J., Qu, S.-L., Zhuo, Q., Wang, W.-Y.: Automatic text detection in complex color images. In: Proc. of Intl. Conf. on Machine Learning and Cybernetics (2002)Google Scholar
- 5.Yuan, Q., Tan, C.L.: Text Extraction from Gray Scale Document Images Using Edge Information. In: Proc. of Sixth Intl. Conf. on Document Analysis and Recognition (2001)Google Scholar
- 12.Pun, C.M., Lee, M.C.: Log-polar wavelet energy signature for rotation and scale invariant texture classification. IEEE Trans. PAMI 25(5), 590–603 (2003)Google Scholar
- 13.Harris, C., Stephens, M.: A combined corner and edge detector. In: Proc. 4th Alvey Vision Conf., pp. 147–151 (1988)Google Scholar