Synthetic data for text localisation in natural images

Conference item

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: Peer reviewed
• Publisher: IEEE
• Host title: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
• Pages: 2315-2324
• Publication date: 2016-12-12
• Acceptance date: 2016-03-02
• Event title: 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016)
• Event location: Las Vegas, NV, USA
• Event website: https://cvpr2016.thecvf.com/
• Event start date: 2016-06-26
• Event end date: 2016-07-01
• DOI: 10.1109/CVPR.2016.254
• EISSN: 1063-6919
• EISBN: 9781467388511
• ISBN: 9781467388528
• Language: English
• Keywords: proposals; pipelines; text recognition; image segmentation; image color analysis; feature extraction; detectors