Text Detection and Language Identification on Natural Scene Images using Faster R-CNN

Abstract

In a world filled with a great deal of linguistic diversity, it can sometimes be difficult to identify signs, markings, or documents that are perhaps in another language. Text detection and language identification are the most critical steps for a language translator working with natural scene images. Here, we present a method for detecting text and language in images by utilizing a Faster Region-based Convolutional Neural Network trained on labelled natural scene images of text in multiple languages.