원문정보
피인용수 : 0건 (자료제공 : 네이버학술정보)
초록
영어
This paper proposes a new classification method for Farsi handwritten word recognition using a scale invariant gradient based features. The extracted feature vectors classified using MLPs. Outputs of MLPs are then combined by Decision Templates. 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. Zoning
2.2. Projection histogram
2.3. Gradient feature
2.4. Wavelet transform
2.5. Vertical and horizontal cross count
2.6. Proposed method
3. Classifier fusion
3.1. Decision templates
4. Experimental results
5. Conclusions
References
1. Introduction
2. Feature Extraction
2.1. Zoning
2.2. Projection histogram
2.3. Gradient feature
2.4. Wavelet transform
2.5. Vertical and horizontal cross count
2.6. Proposed method
3. Classifier fusion
3.1. Decision templates
4. Experimental results
5. Conclusions
References
저자정보
참고문헌
자료제공 : 네이버학술정보