Primary sources: Difference between revisions
No edit summary |
|||
| Line 2: | Line 2: | ||
When working with digitized documents, Optical Character Recognition (OCR) is | When working with digitized documents, Optical Character Recognition (OCR) is | ||
traditionally used to recognized words character-by-character. However, in the | traditionally used to recognized words character-by-character. However, in the | ||
case of offline handwritten text recognition, it does perform poorly. | case of offline handwritten text recognition, it does perform poorly. A more | ||
adapted technology to this kind of document is Word Spotting <ref>Rath, T. M., & | |||
Word spotting for historical documents. International Journal on Document | Manmatha, R. (2007). Word spotting for historical documents. International | ||
Analysis and Recognition, 9(2), 139-152.</ref>. | Journal on Document Analysis and Recognition, 9(2), 139-152.</ref>. This | ||
the words, but it characterizes them by their shape. Then a user can query | technique does not try to directly recognize the words, but it characterizes | ||
either a word either an example (an image) and the system will return all | them by their shape. Then a user can query either a word either an example (an | ||
matching occurrences. The current best results for Word Spotting using strings | image) and the system will return all matching occurrences. | ||
as queries are obtained using Neural Networks, however they require a learning | |||
set and a segmentation by word, which can also be source of errors <ref>Giotis, | The current best results for Word Spotting using strings as queries are obtained | ||
A. P., Sfikas, G., Gatos, B., & Nikou, C. (2017). A survey of document image | using Neural Networks, however in order to obtain good results, they require a | ||
word spotting techniques. Pattern Recognition, 68, 310-332.</ref>. Finally, new | learning set and a segmentation by word, which can also be source of errors | ||
segmentation-free Word Spotting methods have appeared and | <ref>Giotis, A. P., Sfikas, G., Gatos, B., & Nikou, C. (2017). A survey of | ||
<ref>Wilkinson, T., Lindström, J., & Brun, A. (2017). Neural Ctrl-F: | document image word spotting techniques. Pattern Recognition, 68, | ||
Segmentation-free Query-by-String Word Spotting in Handwritten Manuscript | 310-332.</ref>. Finally, new segmentation-free Word Spotting methods have | ||
Collections. arXiv preprint arXiv:1703.07645.</ref>. | appeared and seem to show good results. <ref>Wilkinson, T., Lindström, J., & | ||
Brun, A. (2017). Neural Ctrl-F: Segmentation-free Query-by-String Word Spotting | |||
in Handwritten Manuscript Collections. arXiv preprint arXiv:1703.07645.</ref>. | |||
<references /> | <references /> | ||
Revision as of 20:16, 2 November 2017
Bibliography and state of the art
When working with digitized documents, Optical Character Recognition (OCR) is traditionally used to recognized words character-by-character. However, in the case of offline handwritten text recognition, it does perform poorly. A more adapted technology to this kind of document is Word Spotting [1]. This technique does not try to directly recognize the words, but it characterizes them by their shape. Then a user can query either a word either an example (an image) and the system will return all matching occurrences.
The current best results for Word Spotting using strings as queries are obtained using Neural Networks, however in order to obtain good results, they require a learning set and a segmentation by word, which can also be source of errors [2]. Finally, new segmentation-free Word Spotting methods have appeared and seem to show good results. [3].
- ↑ Rath, T. M., & Manmatha, R. (2007). Word spotting for historical documents. International Journal on Document Analysis and Recognition, 9(2), 139-152.
- ↑ Giotis, A. P., Sfikas, G., Gatos, B., & Nikou, C. (2017). A survey of document image word spotting techniques. Pattern Recognition, 68, 310-332.
- ↑ Wilkinson, T., Lindström, J., & Brun, A. (2017). Neural Ctrl-F: Segmentation-free Query-by-String Word Spotting in Handwritten Manuscript Collections. arXiv preprint arXiv:1703.07645.