Text Region Verification in Natural Scene Images using Multi-resolution Wavelet Transform and Support Vector Machine


The KIPS Transactions:PartB , Vol. 11, No. 6, pp. 667-674, Oct. 2004
10.3745/KIPSTB.2004.11.6.667,   PDF Download:

Abstract

Extraction of texts from images is a fundamental and important problem to understand the images. This paper suggests a text region verification method by statistical means of stroke features of the characters. The method extracts 36 dimensional features from 16x16 sized text and non-text images using wavelet transform - these 36 dimensional features express stroke and direction of characters - and select 12 subfeatures out of 36 dimensional features which yield adequate separation between classes. After selecting the features, SVM trains the selected features. For the verification of the text region, each 16x16 image block is scanned and classified as text or non-text. Then, the text region is finally decided as text region or non-text region. The proposed method is able to verify text regions which can hardly be distin guished.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
K. S. Bae and Y. W. Choi, "Text Region Verification in Natural Scene Images using Multi-resolution Wavelet Transform and Support Vector Machine," The KIPS Transactions:PartB , vol. 11, no. 6, pp. 667-674, 2004. DOI: 10.3745/KIPSTB.2004.11.6.667.

[ACM Style]
Kyung Sook Bae and Yeong Woo Choi. 2004. Text Region Verification in Natural Scene Images using Multi-resolution Wavelet Transform and Support Vector Machine. The KIPS Transactions:PartB , 11, 6, (2004), 667-674. DOI: 10.3745/KIPSTB.2004.11.6.667.