Computer recognition of on-line, hand-written characters [by] M. I. Bernstein.
ResearchPublished 1964
Discussion of a method for recognizing single, hand-written characters using an on-line graphical input device, such as a digitizing pantograph, light pen, or RAND Graphic Input Tablet, as the primary information source. Basically, the method consists of filtering and smoothing the input stream to eliminate as much redundancy as possible. Direction of the stylus movement is quantized into one of the eight directions, allowing each stroke of a character to be described as a series of connected straight-line segments. By eliminating various measures on the stroke, the description is size-, position-, and rotation-independent. To restore some rotational orientation and to discriminate among open, closed, and multistroke characters, end-point comparisons are added to the description.
Document Details
- Copyright: RAND Corporation
- Availability: Web Only
- Year: 1964
- Pages: 33
- DOI: https://doi.org/10.7249/pubs
- Document Number: RM-3753-ARPA
Citation
RAND Style Manual
Chicago Manual of Style
This publication is part of the RAND research memorandum series. The research memorandum series, a product of RAND from 1948 to 1973, included working papers meant to report current results of RAND research to appropriate audiences.
This document and trademark(s) contained herein are protected by law. This representation of RAND intellectual property is provided for noncommercial use only. Unauthorized posting of this publication online is prohibited; linking directly to this product page is encouraged. Permission is required from RAND to reproduce, or reuse in another form, any of its research documents for commercial purposes. For information on reprint and reuse permissions, please visit www.rand.org/pubs/permissions.
RAND is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.