NIST, under sponsorship from the Bureau of the Census, has collected a database consisting of 2,100 pages of binary image data of handprinted characters including numerals and text. NIST Special Database 1 contains handwriting samples from 2,100 writers geographically distributed across the United States, NIST is currently using this database to research field-isolation, box detection and removal, character segmentation, and writer-independent neural character recognition. In addition to advancing the design of algorithms, this database and its study can aid the social sciences. Observations can be compiled and used to improve form design and field layout strategies. Region-based studies and comparisons are also possible due to regionally distributed and referenced populations of writers in the database. In creating this large database, obstacles to the effective archiving of images have been dealt with and eliminated. This paper describes the database's content in terms of its collection, organization, and usefulness. The strategies and conventions used to develop NIST Special Database 1 can be applied to any discipline requiring the use of image archives.
Get full access to this article
View all access options for this article.
References
1.
CCITT (1984). Facsimile coding schemes and coding control functions for group 4 facsimile apparatus, fascicle VII.3-Rec. T.6.
2.
Department of Defense (1988, 20 December). Military specification-raster graphics representation in binary format, requirements for, MIL-R-28002.
3.
GarrisM. D., WilkinsonR. A., & WilsonC. L. (1991, July). Methods for enhancing neural network handwritten character recognition. In Proc. of the IJCNN, vol. 1, 695–700.
4.
WilsonC. L. Forthcoming. A new self-organizing neural network architecture for parallel multi-map pattern recognition—FAUST.Progress in Neural Networks4.
5.
WilsonC. L., & GarrisM. D. (1990, April 18). Handprinted character database,NIST Special Database 1. HWDB.
