Synthetic data for text localisation in natural images

Internet publication

In this paper we introduce a new method for text detection in natural images. The method comprises two contributions: First, a fast and scalable engine to generate synthetic images of text in clutter. This engine overlays synthetic text to existing background images in a natural way, accounting for the local 3D scene geometry. Second, we use the synthetic images to train a Fully-Convolutional Regression Network (FCRN) which efficiently performs text detection and bounding-box regression at all locations and multiple scales in an image. We discuss the relation of FCRN to the recently-introduced YOLO detector, as well as other end-to-end object detection systems based on deep learning. The resulting detection network significantly out performs current methods for text detection in natural images, achieving an F-measure of 84.2% on the standard ICDAR 2013 benchmark. Furthermore, it can process 15 images per second on a GPU.

Authors: Gupta, A; Vedaldi, A; Zisserman, A

• Publication status: Published
• Peer review status: Not peer reviewed
• Host title: arXiv
• Publication date: 2016-04-22
• DOI: 10.48550/arxiv.1604.06646
• Language: English