Text image matching without language model using a Hausdorff distance

Authors:
Hwa-Jeong Son;Soo-Hyung Kim;Ji-Soo Kim
Affiliations:
Department of Computer Science, Chonnam National University, 300, Yongbong-dong, Buk-gu, Gwangju 500-757, South Korea;Department of Computer Science, Chonnam National University, 300, Yongbong-dong, Buk-gu, Gwangju 500-757, South Korea;Department of Computer Science, Chonnam National University, 300, Yongbong-dong, Buk-gu, Gwangju 500-757, South Korea
Venue:
Information Processing and Management: an International Journal
Year:
2008

Citing 6
Cited 1

Imaged Document Text Retrieval Without OCR

IEEE Transactions on Pattern Analysis and Machine Intelligence
Comparing Images Using the Hausdorff Distance

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Method for Character String Extraction Using Local and Global Segment Crowdedness

ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 2 - Volume 2
A Segmentation-free Approach for Keyword Search in Historical Typewritten Documents

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
A document image preprocessing system for keyword spotting

ICADL'04 Proceedings of the 7th international Conference on Digital Libraries: international collaboration and cross-fertilization
Object matching algorithms using robust Hausdorff distance measures

IEEE Transactions on Image Processing

Polyline approach for approximating Hausdorff distance between planar free-form curves

Computer-Aided Design

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a text matching method for document image retrieval without any language model. Two word images are first normalized to an appropriate size and image features are extracted using the local crowdedness method. Similarity between the two features is then measured by calculating a Hausdorff distance. We performed three experiments. The first experiment proves the effectiveness of the proposed method for text matching, and the other two experiments verify the language independence and font size independence of the proposed method.