Capsule-Based Persian/Arabic Robust Handwritten Digit Recognition Using EM Routing
This addresses digit recognition for Persian/Arabic scripts, but it is incremental as it applies an existing method (CapsNet) to a specific language domain.
The paper tackles Persian/Arabic handwritten digit recognition using a capsule network (CapsNet) trained on the Hoda dataset, achieving results that outperform previous methods.
In this paper, the problem of handwritten digit recognition has been addressed. However, the underlying language is Persian/Arabic, and the system with which this task is a capsule network (CapsNet) has recently emerged as a more advanced architecture than its ancestor, namely CNN (Convolutional Neural Network). The training of the architecture is performed using the Hoda dataset, which has been provided for Persian/Arabic handwritten digits. The output of the system clearly outperforms the results achieved by its ancestors, as well as other previously presented recognition algorithms.