@inproceedings{d142fbe31fcf431b9b03f7d47b620734,
title = "Text region extraction and text segmentation on camera-captured document style images",
abstract = "In this paper, we propose a text extraction method from camera-captured document style images and propose a text segmentation method based on a color clustering method. The proposed extraction method detects text regions from the images using two low-level image features and verifies the regions through a high-level text stroke feature. The two level features are combined hierarchically, The low-level features are intensity variation and color variance. And, we use text strokes as a high-level feature using multi-resolution wavelet transforms on local image areas. The stroke feature vector is an input to a SVM (Support Vector Machine) for verification, when needed. The proposed text segmentation method uses color clustering to the extracted text regions. We improved K-means clustering method and it selects K and initial seed values automatically. We tested the proposed methods with various document style images captured by three different cameras. We confirmed that the extraction rates are good enough to be used in real-life applications.",
author = "Song, {Y. J.} and Kim, {K. C.} and Choi, {Y. W.} and Byun, {H. R.} and Kim, {S. H.} and Chi, {S. Y.} and Jang, {D. K.} and Chung, {Y. K.}",
year = "2005",
doi = "10.1109/ICDAR.2005.234",
language = "English",
isbn = "0769524206",
series = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",
pages = "172--176",
booktitle = "Proceedings of the Eighth International Conference on Document Analysis and Recognition",
note = "8th International Conference on Document Analysis and Recognition ; Conference date: 31-08-2005 Through 01-09-2005",
}