Share Email Print

Proceedings Paper

Performance evaluation for line-drawing recognition systems
Author(s): Ihsin T. Phillips; Frank Chang; Kevin Chang; Bhavani Duggirala; Mike Logan; Joe Loughry; Jisheng Liang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper, we discuss a performance evaluator for line- drawing recognition systems on images that contain binary digital logic schematic diagrams, a restricted subclass of engineering line drawings. The evaluator accepts inputs of IGES files containing IGES primitives of straight lines, circles, partial arcs of circles, and IGES label block objects. Our evaluator takes two IGES files. One of these files is the recognition algorithm's output and the other IGES file is the corresponding ground truth. The first step of processing involves parsing each IGES file and extracting IGES entities and the parameter information according to the IGES file format specification. The evaluator performs the evaluation for each pair of entities within these two files based on their types and the matching protocols and matching criteria defined in this paper. The results of our evaluator is a table of numbers which when weighted by application specific weights can be summed to produce an overall score relevant to the application.

Paper Details

Date Published: 3 April 1997
PDF: 13 pages
Proc. SPIE 3027, Document Recognition IV, (3 April 1997); doi: 10.1117/12.270066
Show Author Affiliations
Ihsin T. Phillips, Seattle Univ. (United States)
Frank Chang, Seattle Univ. (United States)
Kevin Chang, Seattle Univ. (United States)
Bhavani Duggirala, Seattle Univ. (United States)
Mike Logan, Seattle Univ. (United States)
Joe Loughry, Seattle Univ. (United States)
Jisheng Liang, Univ. of Washington (United States)

Published in SPIE Proceedings Vol. 3027:
Document Recognition IV
Luc M. Vincent; Jonathan J. Hull, Editor(s)

© SPIE. Terms of Use
Back to Top