In:
Advanced Materials Research, Trans Tech Publications, Ltd., Vol. 490-495 ( 2012-3), p. 76-80
Abstract:
This paper proposes a system, which can rapidly count votes in traditional elections based on image understanding. Firstly, the system gets ballot images through high-speed scanner and preprocesses the images. Then, it recognizes the geometric structure and layout of ballot image through detecting table lines. In addition, it also recognizes the logical structure of ballot image through analyzing the relative positions of candidates and vote symbols. Thirdly, it locates candidates and symbols on the ballot table, and recognizes the specific symbols based on run features. The system has been implemented, which shows high counting speed, high recognition accuracy with wide applicability.
Type of Medium:
Online Resource
ISSN:
1662-8985
DOI:
10.4028/www.scientific.net/AMR.490-495
DOI:
10.4028/www.scientific.net/AMR.490-495.76
Language:
Unknown
Publisher:
Trans Tech Publications, Ltd.
Publication Date:
2012
detail.hit.zdb_id:
2265002-7
Permalink