Text Annotation for Images


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.

Last edited:


Staff member
Mar 21, 2021

VIA (VGG Image Annotator) is a set of open source tools for manual annotation of images and video. The Visual Geometry Group (VGG) has been developing, maintaining and supporting VIA since 2016. In this video, Abhishek Dutta demonstrates the VIA tools and talks about how VIA is being used in research. This video was recorded during the VGG Meeting of Nov. 3, 2020. For more details see the following:

VIA Software page: http://www.robots.ox.ac.uk/~vgg/softw...
VIA Code repository: https://gitlab.com/vgg/via/
LISA Code repository: https://gitlab.com/vgg/lisa