Earticle

초록

영어

This paper proposes a new classification method for Farsi handwritten word recognition using gradient and gradient based features. The extracted feature vectors were classified using two Multi Layer Perceptron networks as basic experts, and one Radial Basis Function was applied to choose the best expert. The experiments were performed using the Iranshahr dataset. This dataset consists of 780 samples of 30 city names of Iran out of which, 600 samples were used to train the network and 180 samples to test it. A set of experiments were conducted to compare proposed method with some other combination rules. Results show that the proposed method achieved 91.11% recognition rate.

목차

Abstract
 1. Introduction
 2. Correlation Reduction Strategies in Multiple Classifier Systems
  2.1. Different representation of patterns
  2.2 Different Learning Machines
  2.3 Different Labeling in Learning
 3. Feature Extraction
  3.1. Gradient
  3.2. Gradient Based Feature Extraction Method
  3.3. Principal Component Analysis (PCA)
  3.4. Linear Discriminate Analysis (LDA)
 4. Proposed New Combination Method Based on Different Representation of Data
 5. Experimental Results
 6. Conclusion
 References

키워드

저자

• Reza Ebrahimpour [ Department of Electrical Engineering, Shahid Rajaee Teachers Training University ]
• Mona Amini [ Mechatronics Engineering in Department of Mechatronics Engineering, Islamic Azad University, South Tehran Branch, Tehran, Iran ]
• Afra Vahidi Shams [ Mechatronics Engineering in Department of Mechatronics Engineering, Islamic Azad University, South Tehran Branch, Tehran, Iran ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Hybrid Information Technology

• 간기

  격월간

• pISSN

  1738-9968

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605