EASTER: Simplifying Text Recognition using only 1D Convolutions

Recurrent units and complex gated layers are key components of most text recognition models. Their sequential nature and complex mechanisms require large labelled training datasets, high computational requirements and lead to slower inference times. In this paper, we present an Efficient And Scalable TExt Recognizer (EASTER) to perform optical character recognition on both machine printed and handwritten text. Our model utilises only 1-D convolutional layers without any recurrence or complex gating mechanisms. Our proposed architecture achieves performance similar to best perform- ing recurrent architectures by using only 4% of training data for offline handwritten text recognition task. We present results of our model on different machine printed text recognition datasets as well. We also showcase improvements over the current best results on line level offline handwritten text recognition task. Our work presents a highly scalable and deployable model for real-world settings while being highly performant.