TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Scene Text Detection	ICDAR 2013	Gupta et al.	F-Measure	83.0%	# 12
Scene Text Detection	ICDAR 2013	Gupta et al.	Precision	92.0	# 6
Scene Text Detection	ICDAR 2013	Gupta et al.	Recall	75.5	# 12

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/synthetic-data-for-text-localisation-in/scene-text-detection-on-icdar-2013)](https://paperswithcode.com/sota/scene-text-detection-on-icdar-2013?p=synthetic-data-for-text-localisation-in)`

Synthetic Data for Text Localisation in Natural Images

CVPR 2016 · Ankush Gupta, Andrea Vedaldi, Andrew Zisserman ·

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.