earticle

논문검색

Common Techniques and Bio-Inspired Hierarchical Architecture for Automatic Farsi Handwritten Word Recognition Systems

초록

영어

This paper investigates Farsi handwritten word recognition using common features. Also we applied biologically inspired features (BIFs), derived from a feed forward model of object recognition pathway in visual cortex for Farsi handwritten word recognition problem. Experimental results show that the model achieves high recognition percentage even for large variations and applicability of these features in Small Sample Size problems (SSS).The experiments were achieved using the Iranshahr dataset. This dataset consist of 780 samples of 30 city names of Iran which 600 samples for train and 180 samples for test was used. A set of experiments were conducted to compare Decision Templates with some combination rules. Results show that template based fusion method is superior to the other schemes.

목차

Abstract
 1. Introduction
 2. Feature Extraction
  2.1. Histogram
  2.2. Characteristic Loci
  2.3. Zoning
  2.4. Wavelet Transform
  2.5. Discrete Cosine Transform
  2.6. Gradient
  2.7. Cross Count
  2.8. Principle Component Analysis
 3. Biological Feature Extraction Method
  3.1. Image Layer
  3.2. S1 and C1Layers
  3.3. S2 andC2 Layers
  3.4. C3 andS3 Layers
  3.5. S2b and C2b Layers
 4. K-Nearest Neighbor Classification
 5. Experimental Results
  5.1. Experiment I
  5.2. Experiment II
  5.3. Experiment III
 6. Conclusions
 References

저자정보

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

참고문헌

자료제공 : 네이버학술정보

    함께 이용한 논문

      ※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

      0개의 논문이 장바구니에 담겼습니다.