Imaged document text retrieval without OCR

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volumn 24, Issue 6, 2002, Pages 838-844

  Tan, Chew Lim ^a,b   Huang, Weihua ^b   Yu, Zhaohui ^c   Xu, Yi ^d  

^a IEEE   (Singapore)

^b NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

^c Agilent Technologies Singapore Pte Ltd ^*  (Canada)

^d AGILENT TECHNOLOGIES   (Singapore)

Author keywords

Document image analysis; Document vector; Text retrieval; Text similarity

Indexed keywords

CHARACTER RECOGNITION; DATABASE SYSTEMS; FEATURE EXTRACTION; IMAGE SEGMENTATION; INFORMATION RETRIEVAL SYSTEMS; TEXT PROCESSING; VECTORS;

TEXT RETRIEVAL;

IMAGE RETRIEVAL;

EID: 0036603179     PISSN: 01628828     EISSN: None     Source Type: Journal    
DOI: 10.1109/TPAMI.2002.1008389     Document Type: Article

References (15)

1. Probabilistic retrieval of OCR degraded text using N-grams
2. An evaluation of information retrieval accuracy with simulated OCR output
3. Gauging similarity via N-grams: Language-independent sorting, categorization, and retrieval of text
4. Performance of text retrieval systems
5. Extraction of indication summary sentences from imaged-documents
6. Detection and location of multi-character sequences in lines of imaged text
7. Content-based indexing and retrieval method of chinese document images
8. Duplicated document detection by template matching
9. Document image similarity and equivalence detection
10. Duplication detection for symbolically compressed documents
11. Determination of the script and language content of document images
12. Categorizing document images into script and language classes
13. Language identification in multilingual documents