Abstract | ||
---|---|---|
Transcript mapping refers to the process of aligning meaningful units of a handwritten document image (e.g. text lines, words, characters) with the corresponding transcription information. It has many applications such as (i) fast generation of ground truth at different granularity levels and (ii) indexing handwritten collections far document retrieval. In this paper, a novel transcript mapping technique is proposed which is guided by the number of words as well as the characters per word of a text line. The proposed method combines the results of a local and a global approach using a scoring algorithm. The efficiency of the proposed method is demonstrated by experimentation conducted on a known, publicly available dataset, achieving word level alignment accuracy of 99.48%. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICFHR.2014.15 | 2014 14TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR) |
Keywords | Field | DocType |
transcript mapping, word segmentation | Pattern recognition,Computer science,Document processing,Speech recognition,Artificial intelligence,Intelligent word recognition | Conference |
ISSN | Citations | PageRank |
2167-6445 | 1 | 0.35 |
References | Authors | |
10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nikolaos Stamatopoulos | 1 | 34 | 2.78 |
Basilis Gatos | 2 | 773 | 43.34 |
Georgios Louloudis | 3 | 81 | 9.54 |