2009
DOI: 10.1016/j.imavis.2009.04.006
|View full text |Cite
|
Sign up to set email alerts
|

1-D chaincode pattern matching for compression of Bi-level printed farsi and arabic textual images

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2012
2012
2016
2016

Publication Types

Select...
3

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(1 citation statement)
references
References 23 publications
0
1
0
Order By: Relevance
“…Nevertheless, the existing feature types and extraction techniques are mostly for the digit code with continuous stroke. [6][7][8][9] The most popular feature is the direction feature, which can be measured from skeleton, 10 chaincode, 11 or gradient. 12 And in addition some complementary features such as structural and concavity feature, 13,14 pro¯le shape feature, 15 and curvature feature 16 yield high performance for continuous character identi¯cation.…”
Section: Introductionmentioning
confidence: 99%
“…Nevertheless, the existing feature types and extraction techniques are mostly for the digit code with continuous stroke. [6][7][8][9] The most popular feature is the direction feature, which can be measured from skeleton, 10 chaincode, 11 or gradient. 12 And in addition some complementary features such as structural and concavity feature, 13,14 pro¯le shape feature, 15 and curvature feature 16 yield high performance for continuous character identi¯cation.…”
Section: Introductionmentioning
confidence: 99%