Handwritten digit recognition is a basic and important problem in computer vision. While it has been studied intensively, the newer datasets keep bring new challenges to existed solutions. A new Kannada-MNIST dataset is mainly digital images of the Kannada language, which contains 70,000 28×28 gray-scale sample images and 10 classes. It also contains a Dig-MNIST dataset, which is an out-of domain test sample dataset and a more challenging test dataset for recognition. In this paper, we evaluate the state-of-art deep learning models for Kannada-MNIST and improve their performance with data augmentation and transfer learning techniques. We manage to achieve a best accuracy of 90.27% for Dig-MNIST in the literature with Inception Model.