Indexing handwriting using word matching

Abstract

There are many historical manuscripts written in a single hand which it would be useful to index. Examples include the W. B. DuBois collection at the University of Massachusetts and the early Presidential libraries at the Library of Congress. The standard technique for indexing documents is to scan them in, convert them to machine readable form (ASCII) using Optical Character Recognition (OCR) and then index them using a text retrieval engine. However, OCR does not work well on handwriting. Here an alternative scheme is proposed for indexing such texts. Each page of the document is segmented into words. The images of the words are then matched against each other to create equivalence classes (each equivalence classes contains multiple instances of the same word). The user then provides ASCII equivalents for say the top 2000 equivalence classes. The current paper deals with the matching aspects of this process. Due to variations in even a single person's handwriting, it is expected that the matching will be the most difficult step in the whole process. A matching technique based on Euclidean distance mapping is discussed. Experiments are shown demonstrating the feasibility of the approach.

Studies of Radical Model for Retrieval of Cursive Chinese Handwritten Annotations

“…This technique can be used in a document annotating and browsing system, which enables users to search their personal notes by a handwritten query. Similar work and various applications also appear elsewhere [6,7].…”

Features for word spotting in historical manuscripts

“…The word spotting idea for handwritten manuscripts was initially proposed by Manmatha et al [4,5]. They presented preliminary work on matching techniques and "pruning" methods, which can quickly discard unlikely matches for a given word by using simple word features such as the aspect ratio of a word's bounding box.…”

“…The word spotting idea has been previously proposed as an alternative solution to this problem for single-author document collections [4,5]. The approach is to segment pages into words, match the words as images, and use the match scores to cluster word images.…”

Multimedia Indexing and Retrieval Research at the Center for Intelligent Information Retrieval

“…It works poorly if the originals are of poor quality or if the text is handwritten. Since Optical Character Recognition (OCR) does not work well on handwriting, an alternative scheme based on matching the images of the words was proposed by us in [18,17,15] for indexing such texts.…”