International Journal of Advance Computational Engineering and Networking (IJACEN)
Follow Us On :
current issues
Volume-12,Issue-2  ( Feb, 2024 )
Past issues
  1. Volume-12,Issue-1  ( Jan, 2024 )
  2. Volume-11,Issue-12  ( Dec, 2023 )
  3. Volume-11,Issue-11  ( Nov, 2023 )
  4. Volume-11,Issue-10  ( Oct, 2023 )
  5. Volume-11,Issue-9  ( Sep, 2023 )
  6. Volume-11,Issue-8  ( Aug, 2023 )
  7. Volume-11,Issue-7  ( Jul, 2023 )
  8. Volume-11,Issue-6  ( Jun, 2023 )
  9. Volume-11,Issue-5  ( May, 2023 )
  10. Volume-11,Issue-4  ( Apr, 2023 )

Statistics report
Jun. 2024
Submitted Papers : 80
Accepted Papers : 10
Rejected Papers : 70
Acc. Perc : 12%
Issue Published : 134
Paper Published : 1567
No. of Authors : 4088
  Journal Paper

Paper Title :
Marathi Character Recognition Using Ant Miner Algorithm

Author :Urmila Shinde, Vanita Mane, Rajashree Shedge

Article Citation :Urmila Shinde ,Vanita Mane ,Rajashree Shedge , (2014 ) " Marathi Character Recognition Using Ant Miner Algorithm " , International Journal of Advance Computational Engineering and Networking (IJACEN) , pp. 101-107, Volume-2,Issue-10

Abstract : Optical Character Recognition (OCR) is an interesting and challenging field of research in pattern recognition, artificial intelligence and machine vision and is used in many real life applications. The work done for the recognition of Devanagari handwritten script is negligible in literature despite it is being used by millions people in India and abroad and it has numerous applications. Research on Optical Character Recognition OCR of Devnagari script is very challenging due to the complex structural properties of the script that are not observed in most other scripts. Devnagari is the script for Marathi. The Marathi language contains 49 distinct characters, 12 vowels and 37 consonants. Recognition of Devnagari characters poses great challenge due to the large variety of symbols and their proximity in appearance. Feature extraction and classification are the two very important steps in Optical character recognition. In this paper we have used three sets of feature extraction techniques namely Hu’s moment invariant, zoning with Hu moment and Zoning with Hu’s moment and radon transform. Here we have proposed Ant Miner Algorithm (AMA) for classification. The AMA is a rule-based approach. The rules are incrementally tuned during the training. The result of this experiment is a 96.94% recognition rate of the training set and 82.21% recognition rate of unseen data test

Type : Research paper

Published : Volume-2,Issue-10


Copyright: © Institute of Research and Journals

| PDF |
Viewed - 64
| Published on 2014-10-06
IRAJ Other Journals
IJACEN updates
Paper Submission is open now for upcoming Issue.
The Conference World