There are two purposes in this paper. The one is to compare experimentally the two types of methods of writer identification, structure analysis and pattern matching, and the other is to examine the dependency of identifiability on letters. The material was provided by seven persons who handwrote a sentence of twenty-six letters twenty-five times repeatedly. About a half of the material was used as a sample for learning and the rest was for test. Templates representing persons were constructed from the sample for learning through each of five methods, three of structure analysis S1, S2, S3 and the other two of pattern matching P1, P2. For each character in the sample for test, the distances from it to the templates were evaluated and the person who was the nearest was judged as the writer. Experimentally the average correct identification rate for P1, which is better than P2, was about 85%, while that for S2, which is better than S1 and S3, was about 80%. As far as the methods of structure analysis proposed by us are concerned, they are inferior to the methods of pattern matching. As for sentences, all of the writers were correctly identified. The correct identification rates for HIRAGANA letters are in general greater than those for KATAKANA, which seems to imply that complicated letters transmit us more information about writers than simple letters do.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Mitsu YOSHIMURA, Fumitaka KIMURA, Isao YOSHIMURA, "Experimental Comparison of Two Types of Methods of Writer Identification" in IEICE TRANSACTIONS on transactions,
vol. E65-E, no. 6, pp. 345-352, June 1982, doi: .
Abstract: There are two purposes in this paper. The one is to compare experimentally the two types of methods of writer identification, structure analysis and pattern matching, and the other is to examine the dependency of identifiability on letters. The material was provided by seven persons who handwrote a sentence of twenty-six letters twenty-five times repeatedly. About a half of the material was used as a sample for learning and the rest was for test. Templates representing persons were constructed from the sample for learning through each of five methods, three of structure analysis S1, S2, S3 and the other two of pattern matching P1, P2. For each character in the sample for test, the distances from it to the templates were evaluated and the person who was the nearest was judged as the writer. Experimentally the average correct identification rate for P1, which is better than P2, was about 85%, while that for S2, which is better than S1 and S3, was about 80%. As far as the methods of structure analysis proposed by us are concerned, they are inferior to the methods of pattern matching. As for sentences, all of the writers were correctly identified. The correct identification rates for HIRAGANA letters are in general greater than those for KATAKANA, which seems to imply that complicated letters transmit us more information about writers than simple letters do.
URL: https://global.ieice.org/en_transactions/transactions/10.1587/e65-e_6_345/_p
Copy
@ARTICLE{e65-e_6_345,
author={Mitsu YOSHIMURA, Fumitaka KIMURA, Isao YOSHIMURA, },
journal={IEICE TRANSACTIONS on transactions},
title={Experimental Comparison of Two Types of Methods of Writer Identification},
year={1982},
volume={E65-E},
number={6},
pages={345-352},
abstract={There are two purposes in this paper. The one is to compare experimentally the two types of methods of writer identification, structure analysis and pattern matching, and the other is to examine the dependency of identifiability on letters. The material was provided by seven persons who handwrote a sentence of twenty-six letters twenty-five times repeatedly. About a half of the material was used as a sample for learning and the rest was for test. Templates representing persons were constructed from the sample for learning through each of five methods, three of structure analysis S1, S2, S3 and the other two of pattern matching P1, P2. For each character in the sample for test, the distances from it to the templates were evaluated and the person who was the nearest was judged as the writer. Experimentally the average correct identification rate for P1, which is better than P2, was about 85%, while that for S2, which is better than S1 and S3, was about 80%. As far as the methods of structure analysis proposed by us are concerned, they are inferior to the methods of pattern matching. As for sentences, all of the writers were correctly identified. The correct identification rates for HIRAGANA letters are in general greater than those for KATAKANA, which seems to imply that complicated letters transmit us more information about writers than simple letters do.},
keywords={},
doi={},
ISSN={},
month={June},}
Copy
TY - JOUR
TI - Experimental Comparison of Two Types of Methods of Writer Identification
T2 - IEICE TRANSACTIONS on transactions
SP - 345
EP - 352
AU - Mitsu YOSHIMURA
AU - Fumitaka KIMURA
AU - Isao YOSHIMURA
PY - 1982
DO -
JO - IEICE TRANSACTIONS on transactions
SN -
VL - E65-E
IS - 6
JA - IEICE TRANSACTIONS on transactions
Y1 - June 1982
AB - There are two purposes in this paper. The one is to compare experimentally the two types of methods of writer identification, structure analysis and pattern matching, and the other is to examine the dependency of identifiability on letters. The material was provided by seven persons who handwrote a sentence of twenty-six letters twenty-five times repeatedly. About a half of the material was used as a sample for learning and the rest was for test. Templates representing persons were constructed from the sample for learning through each of five methods, three of structure analysis S1, S2, S3 and the other two of pattern matching P1, P2. For each character in the sample for test, the distances from it to the templates were evaluated and the person who was the nearest was judged as the writer. Experimentally the average correct identification rate for P1, which is better than P2, was about 85%, while that for S2, which is better than S1 and S3, was about 80%. As far as the methods of structure analysis proposed by us are concerned, they are inferior to the methods of pattern matching. As for sentences, all of the writers were correctly identified. The correct identification rates for HIRAGANA letters are in general greater than those for KATAKANA, which seems to imply that complicated letters transmit us more information about writers than simple letters do.
ER -