@inproceedings{c0957b94692d4892a99cd22d1d2363b3,
title = "Transcript mapping for handwritten Arabic documents",
abstract = "Handwriting recognition research requires large databases of word images each of which is labeled with the word it contains. Full images scanned in, however, usually contain sentences or paragraphs of writing. The creation of labeled databases of images of isolated words is usually tedious, requiring a person to drag a rectangle around each word in the full image and type in the label. Transcript mapping is the automatic alignment of words in a text file with word locations in the full image. It can ease the creation of databases for research. We propose the first transcript mapping method for handwritten Arabic documents. Our approach is based on Dynamic Time Warping (DTW) and offers two primary algorithmic contributions. First is an extension to DTW that uses true distances when mapping multiple entries from one series to a single entry in the second series. Second is a method to concurrently map elements of a partially aligned third series within the main alignment. Preliminary results are provided.",
keywords = "Alignment, Arabic script, Handwriting recognition",
author = "Lorigo, \{Liana M.\} and Venu Govindaraju",
year = "2007",
doi = "10.1117/12.696140",
language = "English",
isbn = "0819466131",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
booktitle = "Proceedings of SPIE-IS and T Electronic Imaging - Document Recognition and Retrieval XIV",
address = "United States",
note = "Document Recognition and Retrieval XIV ; Conference date: 30-01-2007 Through 01-02-2007",
}