• Corpus ID: 195931316

NIST Special Database 2 - Structured Forms Database Users' Guide

@inproceedings{Dimmick2017NISTSD,
  title={NIST Special Database 2 - Structured Forms Database Users' Guide},
  author={Darrin L. Dimmick and Michael D. Garris and Charles L. Wilson and Patricia Flanagan},
  year={2017}
}
This report describes the NIST Structured Forms Reference Set database, NIST Special Database 2, containing binary images of synthesized documents. Databases of this magnitude are necessary to further the research and development of automated document processing systems. This database is being distributed as a reference data set to be used by developers of document recognition and data capture systems to test and report results on a common corpus of images derived from structured forms… 

Figures from this paper

Improving document matching performance by local descriptor filtering

TLDR
This paper proposes an effective method aimed at reducing the amount of local descriptors to be indexed in a document matching framework and tests the performance of this filtering step by using ORB and SIFT local detectors and descriptors.

A comparative study of local detectors and descriptors for mobile document classification

TLDR
A classification architecture based on direct matching of local descriptors is used as baseline for the comparative study, and a set of four different key-point detectors and four differentLocal descriptors are tested in all the possible combinations.

Visual appearance based document classification methods: Performance evaluation and benchmarking

  • S. S. BukhariA. Dengel
  • Computer Science
    2015 13th International Conference on Document Analysis and Recognition (ICDAR)
  • 2015
TLDR
This paper presents simple and effective descriptions of different visual appearance based document image classification techniques, and compares their performance on various standard and publicly available datasets, that are differ in degree of image degradations and content variations.

ICDAR2015 competition on smartphone document capture and OCR (SmartDoc)

TLDR
The competition is structured into two independent challenges: smartphone document capture, and smartphone OCR, and the datasets for both challenges are described along with their ground truth, the performance evaluation protocols which were used, and a final results of the participating methods are presented.

References

SHOWING 1-5 OF 5 REFERENCES

Appendix A: Labeled Form Faces 13

  • Appendix A: Labeled Form Faces 13

Military Specification Raster Graphics Representation in Binary Format, Requirements for, MIL-R-28002

    Facsimile Coding Schemes and Coding Control Functions for Group 4 Facsimile Apparatus, Fascicle VII.3 -Rec

    • Facsimile Coding Schemes and Coding Control Functions for Group 4 Facsimile Apparatus, Fascicle VII.3 -Rec
    • 1984

    Manual Pages for Supplied Software NIST Imaging Database 2 -Structured Forms Database Users' Guide file:///C|/Program Files/Qualcomm/Email Data/Attach/nistsd2_ug_A.htm (8 of 12)

    • Manual Pages for Supplied Software NIST Imaging Database 2 -Structured Forms Database Users' Guide file:///C|/Program Files/Qualcomm/Email Data/Attach/nistsd2_ug_A.htm (8 of 12)
    • 2002

    Military Specification Raster Graphics Representation in Binary Format, Requirements for

    • Military Specification Raster Graphics Representation in Binary Format, Requirements for
    • 1988