Abstract
Document image decoding (DID) is a trial to understand the contents of a whole document without any reference information about font, language, etc. Typically, DID approaches assume the correct segmentation of the document and some a priori knowledge about the language or the script. Unfortunately, this assumption will not hold if we deal with various documents, such as documents with various sized fonts, camera-captured documents, free-layout documents, or historical documents. In this paper, we propose a part-based character identification method where no segmentation into characters is necessary and no a priori information about the document is needed. The approach clusters similar key points and groups frequent neighboring key point clusters. Then a second iteration is performed, i.e., the groups are again clustered and optionally pairs frequent group clusters are detected. Our first experimental results on multi font-size documents look already very promising. We could find nearly perfect correspondences between characters and detected group clusters.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 10th IAPR International Workshop on Document Analysis Systems, DAS 2012 |
| Pages | 266-270 |
| Number of pages | 5 |
| DOIs | |
| Publication status | Published - May 24 2012 |
| Event | 10th IAPR International Workshop on Document Analysis Systems, DAS 2012 - Gold Coast, QLD, Australia Duration: Mar 27 2012 → Mar 29 2012 |
Publication series
| Name | Proceedings - 10th IAPR International Workshop on Document Analysis Systems, DAS 2012 |
|---|
Other
| Other | 10th IAPR International Workshop on Document Analysis Systems, DAS 2012 |
|---|---|
| Country | Australia |
| City | Gold Coast, QLD |
| Period | 3/27/12 → 3/29/12 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
Cite this
Toward part-based document image decoding. / Song, Wang; Uchida, Seiichi; Liwicki, Marcus.
Proceedings - 10th IAPR International Workshop on Document Analysis Systems, DAS 2012. 2012. p. 266-270 6195376 (Proceedings - 10th IAPR International Workshop on Document Analysis Systems, DAS 2012).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Toward part-based document image decoding
AU - Song, Wang
AU - Uchida, Seiichi
AU - Liwicki, Marcus
PY - 2012/5/24
Y1 - 2012/5/24
N2 - Document image decoding (DID) is a trial to understand the contents of a whole document without any reference information about font, language, etc. Typically, DID approaches assume the correct segmentation of the document and some a priori knowledge about the language or the script. Unfortunately, this assumption will not hold if we deal with various documents, such as documents with various sized fonts, camera-captured documents, free-layout documents, or historical documents. In this paper, we propose a part-based character identification method where no segmentation into characters is necessary and no a priori information about the document is needed. The approach clusters similar key points and groups frequent neighboring key point clusters. Then a second iteration is performed, i.e., the groups are again clustered and optionally pairs frequent group clusters are detected. Our first experimental results on multi font-size documents look already very promising. We could find nearly perfect correspondences between characters and detected group clusters.
AB - Document image decoding (DID) is a trial to understand the contents of a whole document without any reference information about font, language, etc. Typically, DID approaches assume the correct segmentation of the document and some a priori knowledge about the language or the script. Unfortunately, this assumption will not hold if we deal with various documents, such as documents with various sized fonts, camera-captured documents, free-layout documents, or historical documents. In this paper, we propose a part-based character identification method where no segmentation into characters is necessary and no a priori information about the document is needed. The approach clusters similar key points and groups frequent neighboring key point clusters. Then a second iteration is performed, i.e., the groups are again clustered and optionally pairs frequent group clusters are detected. Our first experimental results on multi font-size documents look already very promising. We could find nearly perfect correspondences between characters and detected group clusters.
UR - http://www.scopus.com/inward/record.url?scp=84862074296&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84862074296&partnerID=8YFLogxK
U2 - 10.1109/DAS.2012.90
DO - 10.1109/DAS.2012.90
M3 - Conference contribution
AN - SCOPUS:84862074296
SN - 9780769546612
T3 - Proceedings - 10th IAPR International Workshop on Document Analysis Systems, DAS 2012
SP - 266
EP - 270
BT - Proceedings - 10th IAPR International Workshop on Document Analysis Systems, DAS 2012
ER -