A Fast Algorithm for Persian Handwritten NumberRecognition with Computational Geometry Techniques
Publish Year: 1393
نوع سند: مقاله ژورنالی
زبان: English
View: 1,234
This Paper With 5 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_ACSIJ-3-3_013
تاریخ نمایه سازی: 5 شهریور 1393
Abstract:
This paper aims to improve the feature extraction of Persian handwritten number recognition systems. In this paper, weintroduced nine new features for detection and recognition of Persian handwritten digits using the technique of finding thesmallest enclosing disc in computational geometry. All these features are based on the geometry form of numbers and aremuch better than the features in terms of accuracy such as gradient which are mentioned as the strongest feature in theliterature. In fact our defined features are highly resistant to resize and rotation operations due to the circular form of Persian digits. In terms of feature extraction performance, our newlydefined features are tested on Hoda database and the calculated results confirmed the efficiency of these features. Due to the improvement of recognition rate and acceptable speed, ourdefined features are better than other common features in digit recognition.
Keywords:
Authors
Keivan Borna
Faculty of Mathematics and Computer Science, Kharazmi University, Tehran, Iran
Vahid Haji Hashemi
Faculty of Engineering, Kharazmi University, Tehran, Iran