Computer Vision group from the University of Oxford
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.
This work was inspired by the success of generative adversarial networks (GANs) for training deep models in unsupervised and semi-supervised settings. We proposed an end-to-end architecture for one-class classification. The architecture is composed of two deep networks, each of which trained by competing with each other while collaborating to understand the underlying concept in the target class, and then classify the testing samples. One network works as the novelty detector, while the other supports it by enhancing the inlier samples and distorting the outliers. The intuition is that the separability of the enhanced inliers and distorted outliers is much better than deciding on the original samples.
Here is the preliminary version of the code on grayscale databases.
The Unified Modeling Language (UML) is widely taught in academia and has good acceptance in industry. However, there is not an ample dataset of UML diagrams publicly available. Our aim is to offer a dataset of UML files, together with meta-data of the software projects where the UML files belong...
This approach can be used to extract images as well (jpg, png, etc.).
Surgeons use information from multiple sources when making surgical decisions. These include volumetric datasets (such as CT, PET, MRI, and their variants), 2D datasets (such as endoscopic videos), and vector-valued datasets (such as computer simulations). Presenting all the information to the...
Compared to natural images, understanding scientific figures is particularly hard for machines. However, there is a valuable source of information in scientific literature that until now has remained untapped: the correspondence between a figure and its caption. In this paper we investigate what can be learnt by looking at a large number of figures and reading their captions, and introduce a figure-caption correspondence learning task that makes use of our observations. Training visual and language networks without supervision other than pairs of unconstrained figures and captions is shown to successfully solve this task. We also show that transferring lexical and semantic knowledge from a knowledge graph significantly enriches the resulting features. Finally, we demonstrate the positive impact of such features in other tasks involving scientific text and figures, like multi-modal classification and machine comprehension for question answering, outperforming supervised baselines and ad-hoc approaches.