Handwritten Tifinagh Characters Recognition Using Deep Convolutional Neural Networks

Handwritten characters recognition is a challenging task due to the diversity of writing styles. In the present paper, a new offline recognition system based on deep convolutional neural networks (CNNs) is designed. It uses CNNs to extract features from raw pixels which makes the proposed technique more flexible than the other conventional ones that require a set of additional preprocessing steps to extract the desired invariants features. The proposed system is tested on the AMHCD data set and achieved the best recognition accuracy (99.10%) compared to the state-of-the-art results.