For the transition from traditional to digital libraries, the large number of handwritten manuscripts that exist pose a great challenge. Easy access to such collections requires an index, which is currently created manually at great cost. Because automatic handwriting recognizers fail on historical manuscripts, the word spotting technique has been developed: the words in a collection are matched as images and grouped into clusters which contain all instances of the same word. By annotating "interesting" clusters, an index that links words to the locations where they occur can be built automatically. Due to the noise in historical documents, selecting the right features for matching words is crucial. We analyzed a range of features suitable for matching words using dynamic time warping (DTW), which aligns and compares sets of features extracted from two images. Each feature's individual performance was measured on a test set. With an average precision of 72%, a combination of features outperforms competing techniques in speed and precision.
Features for word spotting in historical manuscripts
2003-01-01
301207 byte
Conference paper
Electronic Resource
English
Features for Word Spotting in Historical Manuscripts
British Library Conference Proceedings | 2003
|Word spotting in historical documents using primitive codebook and dynamic programming
British Library Online Contents | 2015
|Keyword spotting via word-shape recognition [2422-29]
British Library Conference Proceedings | 1995
|Word Spotting and Out-of-Set Rejection in Voice Control Applications
British Library Conference Proceedings | 1993
|Word spotting and out-of-set rejection in voice control applications
Automotive engineering | 1993
|