Earticle

초록

영어

In this paper we have achieved a comparison between the performances of different types of distances used in the k nearest neighbors classifier for recognition of isolated handwritten Arabic numerals extracted from Mnist database, more precisely these distances are those of Euclid, of Manhathan, of Minkowski, and of Tchebychev, to do this, we have used for pre-processing the image numerals the median filter, the thresholding, the centering and the skeletonization techniques and in order to extract the features from numerals we have employed the zoning method. The simulation results that we obtained demonstrates that all these distances are generally almost equivalents.

목차

Abstract
 1. Introduction
 2. Recognition system
 3. Pre-processing
 4. Features Extraction
 5. Recognition
 6. Experiments and Results
 7. Conclusion
 Acknowledgement
 References

키워드

Isolated handwritten Arabic numerals Mnist database Median filter Thresholding Centering Skeletonization zoning method k-nearest neighbors classifier Euclidean distance Manhathan distance Minkowski distance Tchebychev distance

저자

• B. El Kessab [ Laboratory of Information Processing and Decision Aids, Faculty of Science and Technology, BP 523, Beni Mellal, Morocco ]
• C. Daoui [ Laboratory of Information Processing and Decision Aids, Faculty of Science and Technology, BP 523, Beni Mellal, Morocco ]
• B. Bouikhalene [ Laboratory of Information Processing and Decision Aids, Faculty of Science and Technology, BP 523, Beni Mellal, Morocco ]
• R. Salouan [ Laboratory of Information Processing and Decision Aids, Faculty of Science and Technology, BP 523, Beni Mellal, Morocco ]

참고문헌

발행기관

간행물