Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks
This work addresses the challenge of efficient and integrated text spotting in images for computer vision applications, though it is incremental as it builds on existing convolutional recurrent neural network methods.
The authors tackled the problem of text detection and recognition in natural scene images by proposing a unified network that performs both tasks simultaneously in a single forward pass, achieving competitive performance on benchmark datasets.
In this work, we jointly address the problem of text detection and recognition in natural scene images based on convolutional recurrent neural networks. We propose a unified network that simultaneously localizes and recognizes text with a single forward pass, avoiding intermediate processes like image cropping and feature re-calculation, word separation, or character grouping. In contrast to existing approaches that consider text detection and recognition as two distinct tasks and tackle them one by one, the proposed framework settles these two tasks concurrently. The whole framework can be trained end-to-end, requiring only images, the ground-truth bounding boxes and text labels. Through end-to-end training, the learned features can be more informative, which improves the overall performance. The convolutional features are calculated only once and shared by both detection and recognition, which saves processing time. Our proposed method has achieved competitive performance on several benchmark datasets.