Graph-based keyword spotting in historical handwritten documents

Loading...
Thumbnail Image

Authors

Stauffer, Michael
Fischer, Andreas
Riesen, Kaspar

Journal Title

Journal ISSN

Volume Title

Publisher

Springer

Abstract

The amount of handwritten documents that is digitally available is rapidly increasing. However, we observe a certain lack of accessibility to these documents especially with respect to searching and browsing. This paper aims at closing this gap by means of a novel method for keyword spotting in ancient handwritten documents. The proposed system relies on a keypoint-based graph representation for individual words. Keypoints are characteristic points in a word image that are represented by nodes, while edges are employed to represent strokes between two keypoints. The basic task of keyword spotting is then conducted by a recent approximation algorithm for graph edit distance. The novel framework for graph-based keyword spotting is tested on the George Washington dataset on which a state-of-the-art reference system is clearly outperformed.

Description

Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR). S+SSPR 2016: Structural, Syntactic, and Statistical Pattern Recognition pp. 564-573.

Keywords

Handwritten keyword spotting, Bipartite graph matching, Graph representation for words

Sustainable Development Goals

Citation

Stauffer M., Fischer A., Riesen K. (2016) Graph-Based Keyword Spotting in Historical Handwritten Documents. In: Robles-Kelly A., Loog M., Biggio B., Escolano F., Wilson R. (eds) Structural, Syntactic, and Statistical Pattern Recognition. S+SSPR 2016. Lecture Notes in Computer Science, vol 10029. Springer, Cham.