Farsi/Arabic handwritten digit recognition using quantum neural networks and bag of visual words method
- Авторы: Montazer G.A.1, Soltanshahi M.A.1, Giveki D.1
-
Учреждения:
- School of Engineering, Department of Information Technology Engineering
- Выпуск: Том 26, № 2 (2017)
- Страницы: 117-128
- Раздел: Article
- URL: https://journals.rcsi.science/1060-992X/article/view/194967
- DOI: https://doi.org/10.3103/S1060992X17020060
- ID: 194967
Цитировать
Аннотация
Handwritten digit recognition has long been a challenging problem in the field of optical character recognition and of great importance in industry. This paper develops a new approach for handwritten digit recognition that uses a small number of patterns for training phase. To improve performance of isolated Farsi/Arabic handwritten digit recognition, we use Bag of Visual Words (BoVW) technique to construct images feature vectors. Each visual word is described by Scale Invariant Feature Transform (SIFT) method. For learning feature vectors, Quantum Neural Networks (QNN) classifier is used. Experimental results on a very popular Farsi/Arabic handwritten digit dataset (HODA dataset) show that proposed method can achieve the highest recognition rate compared to other state of the arts methods.
Ключевые слова
Об авторах
Gholam Montazer
School of Engineering, Department of Information Technology Engineering
Автор, ответственный за переписку.
Email: montazer@modares.ac.ir
Иран, Tehran
Mohammad Soltanshahi
School of Engineering, Department of Information Technology Engineering
Email: montazer@modares.ac.ir
Иран, Tehran
Davar Giveki
School of Engineering, Department of Information Technology Engineering
Email: montazer@modares.ac.ir
Иран, Tehran
Дополнительные файлы
