International Journal of Engineering، جلد ۳۴، شماره ۸، صفحات ۲۰۲۸-۲۰۳۷
عنوان فارسی
چکیده فارسی مقاله
کلیدواژه‌های فارسی مقاله
عنوان انگلیسی Holistic Persian Handwritten Word Recognition Using Convolutional Neural Network
چکیده انگلیسی مقاله Due to the cursive-ness and high variability of Persian scripts, the segmentation of handwritten words into sub-words is still a challenging task. These issues could be addressed in a holistic approach by sidestepping segmentation at the character level. In this paper, an end-to-end holistic method based on deep convolutional neural network is proposed to recognize off-line Persian handwritten words. The proposed model uses only five convolutional layers and two fully connected layers for classifying word images effectively, which can lead to a substantial
reduction in parameters. The effect of various pooling strategies is also investigated in this paper. The primary goal of this article is to ignore handcrafted feature extraction and attain a generalized and stable word recognition system. The presented model is assessed using two famous handwritten Persian word databases called Sadri and IRANSHAHR. The recognition accuracies were obtained at 98.6% and 94.6%, on Sadri and IRANSHAHR datasets respectively, and outperformed the state-of-the-art methods.
کلیدواژه‌های انگلیسی مقاله Persian handwritten word recognition,convolutional neural network,End-to-end learning method,Transfer learning,Persian handwritten dataset
نویسندگان مقاله A. Zohrevand |
Computer Engineering Department, Kosar University of Bojnord, Bojnord, Iran

Z. Imani |
Computer Engineering Department, Kosar University of Bojnord, Bojnord, Iran

نشانی اینترنتی https://www.ije.ir/article_133939_817da42bb0a10b58ef95a2eb6d87156c.pdf
فایل مقاله فایلی برای مقاله ذخیره نشده است
کد مقاله (doi)
زبان مقاله منتشر شده en
موضوعات مقاله منتشر شده
نوع مقاله منتشر شده
برگشت به: صفحه اول پایگاه   |   نسخه مرتبط   |   نشریه مرتبط   |   فهرست نشریات