Abstract | ||
---|---|---|
To successfully apply character recognition technology most of the forms currently hand-keyed will need to be redesigned. This paper presents results from a comprehensive study of three versions of a redesigned tax form. Analyses show that using separately spaced character boxes provides superior machine readability over fields containing combs and adjoining character boxes. It is shown that character boxes containing two vertically stacked ovals cause writers much more difficulty. Analyses provide proof that writer idiosyncratic responses on forms are the major source of errors, and proper form design can reduce these errors. |
Year | DOI | Venue |
---|---|---|
1996 | 10.1109/34.506417 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
business forms,financial data processing,human factors,neural nets,optical character recognition,character boxes,form design,handwriting recognition,idiosyncratic response,machine readability,optical character recognition,probabilistic neural networks,tax form | Forms processing,Computer vision,Character recognition,Computer science,Business forms,Handwriting recognition,Optical character recognition,Readability,Speech recognition,Artificial intelligence,Artificial neural network,Financial data processing | Journal |
Volume | Issue | ISSN |
18 | 6 | 0162-8828 |
Citations | PageRank | References |
6 | 0.96 | 3 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael D. Garris | 1 | 15 | 2.60 |
Darrin L. Dimmick | 2 | 7 | 1.39 |