EAST: An Efficient and Accurate Scene Text Detector
This work addresses the need for fast and accurate text detection in images for applications like document analysis and autonomous systems, representing a significant improvement over previous multi-stage methods.
The paper tackles the problem of scene text detection in challenging natural scenes by proposing a simple pipeline that directly predicts text of arbitrary shapes, eliminating intermediate steps. It achieves an F-score of 0.7820 at 13.2fps on the ICDAR 2015 dataset, outperforming state-of-the-art methods in accuracy and efficiency.
Previous approaches for scene text detection have already achieved promising performances across various benchmarks. However, they usually fall short when dealing with challenging scenarios, even when equipped with deep neural network models, because the overall performance is determined by the interplay of multiple stages and components in the pipelines. In this work, we propose a simple yet powerful pipeline that yields fast and accurate text detection in natural scenes. The pipeline directly predicts words or text lines of arbitrary orientations and quadrilateral shapes in full images, eliminating unnecessary intermediate steps (e.g., candidate aggregation and word partitioning), with a single neural network. The simplicity of our pipeline allows concentrating efforts on designing loss functions and neural network architecture. Experiments on standard datasets including ICDAR 2015, COCO-Text and MSRA-TD500 demonstrate that the proposed algorithm significantly outperforms state-of-the-art methods in terms of both accuracy and efficiency. On the ICDAR 2015 dataset, the proposed algorithm achieves an F-score of 0.7820 at 13.2fps at 720p resolution.