OCR-Nets: Variants of Pre-trained CNN for Urdu Handwritten Character Recognition via Transfer Learning
Mohammed Aarif K.O, P. Sivakumar
Abstract
Deep Convolutional neural networks (CNN) have been among the utmost competitive neural network architectures and have set the state-of-the-art in various fields of computer vision. In this paper, we present OCR-Nets, variants of (AlexNet & GoogleNet) for recognition of handwritten Urdu characters through transfer learning. Our proposed networks are experimented using an integrated dataset. To compare the recognition rate with traditional character recognition methods and to confirm the fairness of the experiment an additional Urdu character dataset is manually generated with different fonts and size. The experimental result shows that OCR-AlexNet and OCR-GoogleNet produce significant performance gains of 96.3% and 94.7% averaged success rate respectively.