Libraries contain enormous amounts of handwritten historical documents which cannot be made available on-line because they do not have a searchable index. The wordspotting idea has previously been proposed as a solution to creating indexes for such documents and collections by matching word images. In this paper we present an algorithm which compares whole word-images based on their appearance. This algorithm recovers correspondences of points of interest in two images, and then uses these correspondences to construct a similarity measure. This similarity measure can then be used to rank word-images in order of their closeness to a querying image. We achieved an average precision of 62.57% on a set of 2372 images of reasonable quality and an average precision of 15.49% on a set of 3262 images from documents of poor quality that are even hard to read for humans.
Using Corner Feature Correspondences to Rank Word Images by Similarity
2003-06-01
244973 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Visual Servoing without Feature Correspondences Using Eigenspace Method
British Library Online Contents | 1996
|Unsupervised Feature Learning for Dense Correspondences Across Scenes
British Library Online Contents | 2016
|Removal of specular reflections from image sequences using feature correspondences
British Library Online Contents | 2017
|About the Correspondences of Points Between N Images
British Library Conference Proceedings | 1995
|