%0 Journal Article %T Holistic Persian Handwritten Word Recognition Using Convolutional Neural Network %J International Journal of Engineering %I Materials and Energy Research Center %Z 1025-2495 %A Zohrevand, A. %A Imani, Z. %D 2021 %\ 08/01/2021 %V 34 %N 8 %P 2028-2037 %! Holistic Persian Handwritten Word Recognition Using Convolutional Neural Network %K Persian handwritten word recognition %K convolutional neural network %K End-to-end learning method %K Transfer learning %K Persian handwritten dataset %R 10.5829/ije.2021.34.08b.24 %X 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. %U https://www.ije.ir/article_133939_817da42bb0a10b58ef95a2eb6d87156c.pdf