Intelligent Processing of Visual Media
Lead Research Organisation:
CARDIFF UNIVERSITY
Department Name: Computer Science
Abstract
The proposed research covers a very wide range of topics in processing of digital geometry, images and video sequences, being funded to a total of 24,000,000 Chinese Yuan (about 1,600,000) by the Chinese Ministry of Science and Technology.The topics to be investigated will includeShape, image and video understanding, using neural networks and other ideas based on the structure of the human visual system, with an emphasis on high-performance systemsThe development of mathematical tools which are necessary for processing geometry and image and video understanding, allowing computers to learn about things they see, and to then classify new examples shown to them later. The key issue here is the huge amount of information present in the large numbers of pixels present in images, and even more so in video.How analogies to the human visual system can be used to help develop systems which can understand images and video. This includes such ideas as how to separate the big picture from the small details, using understanding at different geometric scales, and how to make methods which can automatically cluster related information. Further key issues are how geometric and visual information should be acquired and represented so that it can be processed effectively and efficiently to answer queries about content.How key features of geometric shapes, images and video can be represented, stored, compressed and encrypted. Particularly important are issues of digital rights management, including embedding invisible watermarks into visual data to enable proof of ownership, and the ability to provide content-aware security for geometric models, images and video.Other goals include new approaches to capturing and editing geometric models, images and video, including for example video blending.
People |
ORCID iD |
Ralph Martin (Principal Investigator) |
Publications
Zhang Y
(2009)
Shrinkability Maps for Content-Aware Video Resizing
in Computer Graphics Forum
Zhang SH
(2009)
Vectorizing cartoon animations.
in IEEE transactions on visualization and computer graphics
Zhang S
(2009)
Video-based running water animation in Chinese painting style
in Science in China Series F: Information Sciences
Zhang S
(2007)
Video structure analysis
in Tsinghua Science and Technology
Zhang S
(2011)
Online Video Stream Abstraction and Stylization
in IEEE Transactions on Multimedia
Zhang G
(2009)
A Shape-Preserving Approach to Image Resizing
in Computer Graphics Forum
Yan HB
(2008)
Shape deformation using a skeleton to drive simplex transformations.
in IEEE transactions on visualization and computer graphics
Yan H
(2007)
3D Morphing Using Strain Field Interpolation
in Journal of Computer Science and Technology
Shen C
(2010)
Harmonic Field Based Volume Model Construction from Triangle Soup
in Journal of Computer Science and Technology
Ralph Martin (Author)
(2011)
Hidden Images
Description | This project devised a wide range of algorithms for visual computing, based around computer graphics, computer vision, and geometric computing, in collaboration with partners at Tsinghua University in China. Particular topics covered include - analysis of structure and content of video - resizing of images and video for a different screen shape - turning video into a cartoon style animation - morphing of one shape into another - use of skeletons to animate shapes - understanding of tolerances in geometric computations - analysis of small visual differences in shapes represented as meshes - segmentation of video and surface meshes into meaningful components - repair of faulty surface meshes - analyzing images and representing them as simple (vector) components for compression and editing - hiding images within other images |
Exploitation Route | These algorithms have the potential to be used in the creative industries for synthesis, editing, processing and watermarking of images and film, and also for use in computer aided design and manufacture. This work has been reported in leading international conferences and journals, and is available for download from the grant holder's web page. These results are currently being demonstrated to a range of UK and international companies. |
Sectors | Creative Economy,Digital/Communication/Information Technologies (including Software) |
URL | http://ralph.cs.cf.ac.uk/publications.html |
Description | Implemented in various commercial software by Chinese companies such as Tencent. |
First Year Of Impact | 2007 |
Sector | Creative Economy,Digital/Communication/Information Technologies (including Software) |
Impact Types | Societal,Economic |
Description | EPSRC |
Amount | £100,000 (GBP) |
Funding ID | EP/J009830/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 01/2012 |
End | 01/2017 |
Description | Structural analysis and interactive composition of visual media |
Amount | £98,000 (GBP) |
Funding ID | EP/J009830/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 01/2012 |
End | 12/2016 |