@inproceedings{923899b1f2834be7a223cdc42f142ea0,
title = "An HMM-Based Algorithm for Similar Layout Document Image Retrieval",
abstract = "Document image retrieval is an important problem in image processing and is often a crucial step toward recognition and information extraction. In this paper, the problem is retrieving the document image having similar layout with query image. We propose a solution based on two algorithmic ideas. For unconstrained handwritten documents, the image is segmented into text lines using k-means clustering to build a minimum cost spanning tree (MST). Then, a hidden Markov model (HMM) is defined on the tree, the decoding sequence of which represents the layout structure. In this image retrieval system, the candidate images having the same decoding sequence with query image will be sorted by the Manhattan distance, and the nearest images are selected.",
keywords = "HMM, Layout similarity, Text line segmentation",
author = "Jingwen Zhou and Ying Wen and Yue Lu",
year = "2014",
doi = "10.1007/978-3-642-54924-3\_102",
language = "英语",
isbn = "9783642549236",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "1077--1083",
booktitle = "Foundations of Intelligent Systems - Proceedings of the 8th InternationalConference on Intelligent Systems and Knowledge Engineering, ISKE 2013",
address = "德国",
note = "8th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2013 ; Conference date: 20-11-2013 Through 23-11-2013",
}