Correlation filter : an accurate approach to detect and locate low contrast character strings in complex table environment

Correlation has been used extensively in object detection field. In this paper, two kinds of correlation filters, Minimum Average Correlation Energy (MACE) and Extended Maximum Average Correlation Height (EMACH), are applied as adaptive shift locators to detect and locate smudgy character strings in...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 26(2004), 12 vom: 13. Dez., Seite 1639-44
1. Verfasser: Li, Yi (VerfasserIn)
Weitere Verfasser: Wang, Zhiyan, Zeng, Haizan
Format: Aufsatz
Sprache:English
Veröffentlicht: 2004
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM152402004
003 DE-627
005 20231223061934.0
007 tu
008 231223s2004 xx ||||| 00| ||eng c
028 5 2 |a pubmed24n0508.xml 
035 |a (DE-627)NLM152402004 
035 |a (NLM)15573824 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Li, Yi  |e verfasserin  |4 aut 
245 1 0 |a Correlation filter  |b an accurate approach to detect and locate low contrast character strings in complex table environment 
264 1 |c 2004 
336 |a Text  |b txt  |2 rdacontent 
337 |a ohne Hilfsmittel zu benutzen  |b n  |2 rdamedia 
338 |a Band  |b nc  |2 rdacarrier 
500 |a Date Completed 12.01.2005 
500 |a Date Revised 02.12.2004 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Correlation has been used extensively in object detection field. In this paper, two kinds of correlation filters, Minimum Average Correlation Energy (MACE) and Extended Maximum Average Correlation Height (EMACH), are applied as adaptive shift locators to detect and locate smudgy character strings in complex tabular color flight coupon images. These strings in irregular tabular coupon are computer-printed characters but of low contrast and could be shifted out of the table so that we cannot detect and locate them using traditional algorithms. In our experiment, strings are extracted in the preprocessing phase by removing background and then based on geometric information, two correlation filters are applied to locate expected fields. We compare results from two correlation filters and demonstrate that this algorithm is a high accurate approach 
650 4 |a Journal Article 
700 1 |a Wang, Zhiyan  |e verfasserin  |4 aut 
700 1 |a Zeng, Haizan  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 26(2004), 12 vom: 13. Dez., Seite 1639-44  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:26  |g year:2004  |g number:12  |g day:13  |g month:12  |g pages:1639-44 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 26  |j 2004  |e 12  |b 13  |c 12  |h 1639-44