• Skip to content
  • Skip to footer
  • Accessibility options
University of Brighton
  • About us
  • Business and
    employers
  • Alumni and
    supporters
  • For
    students
  • For
    staff
  • Accessibility
    options
Open menu
Home
Home
  • Close
  • Study here
    • Courses and subjects
    • Find a course
    • A-Z course list
    • Explore our subjects
    • Academic departments
    • Visiting the university
    • Explore: get to know us
    • Upcoming events
    • Virtual tours
    • Chat to our students and staff
    • Open days
    • Applicant days
    • Order a prospectus
    • Ask a question
    • Studying here
    • Accommodation and locations
    • Applying
    • Undergraduate
    • Postgraduate
    • Transferring from another university
    • The Student Contract
    • Clearing
    • International students
    • Fees and finance
    • Advice and help
    • Advice for students
    • Advice for parents and carers
    • Advice for schools and teachers
    • Managing your application
    • Undergraduate
    • Postgraduate
    • Apprenticeships
  • Research
    • Research and knowledge exchange
    • Research and knowledge exchange organisation
    • The Global Challenges
    • Centres of Research Excellence (COREs)
    • Research Excellence Groups (REGs)
    • Our research database
    • Information for business
    • Community University Partnership Programme (CUPP)
    • Postgraduate research degrees
    • PhD research disciplines and programmes
    • PhD funding opportunities and studentships
    • How to apply for your PhD
    • Research environment
    • Investing in research careers
    • Strategic plan
    • Research concordat
    • News, events, publications and films
    • Featured research and knowledge exchange projects
    • Research and knowledge exchange news
    • Inaugural lectures
    • Research and knowledge exchange publications and films
    • Academic staff search
  • About us
  • Business and employers
  • Alumni, supporters and giving
  • Current students
  • Staff
  • Accessibility
Search our site

A multi-coloured mix of molecules, columns of numbers and radio waves, depicting modern communications and research into internet security.

Centre for Secure, Intelligent and Usable Systems
  • What we do
  • Join us for study, work or visit
  • Who we are
  • What we do
    • What we do
    • Security
    • Intelligence
    • Usability
    • Our research and enterprise projects
    • Our research and enterprise impact
  • Our research and enterprise projects
    • Our research and enterprise projects
    • EMPOWERCARE
    • 3D-COFORM
    • Accessible Reasoning with Diagrams
    • Adaptation of mobile and distributed systems
    • Automatic semantic analysis of 3D content in digital repositories
    • ChartEx
    • DEFeND Data governance for supporting GDPR
    • Engineering and Evolving Secure Software Systems
    • EPOCH
    • Hove Plinth - Place-based narratives
    • iV&L Net
    • Mesh saliency
    • MITIGATE
    • Real-time automatic label detection on food trays
    • Real-time interactive image segmentation
    • Secure Tropos
    • SESAME
    • The VisiOn project
    • Word sketches
  • Real-time interactive image segmentation

Real-time interactive image segmentation

Introduction to this project here please - what problem is it trying to solve? what are the current issues facing people that it will address?

Project aims

We present a real-time interactive image segmentation system for the semantic analysis of images. It is a feasible solution to a variety of real quality control tasks mainly because it adopts a novel interactive training and classification mode. In general, our system incorporates the interactive acquisition of training data into the automatic classification based on adaptive boosting.

To reduce the manual effort required for interactively acquiring the online training data, the input images are efficiently processed through GPU-based over-segmentation. We also developed a user-friendly graphical user interface to allow users to edit (select, deselect and reselect) the training data. It also allows the users to add more training data to improve the classifier if necessary.

Project findings and impact

The experiments demonstrate that our system efficiently delivers a semantic analysis for images. More importantly, different from the state-of-the-art methods which typically rely on offline training using a large collection of data, our system can rely only on a tiny amount of training data offered by the users in an interactive manner and achieve a highly accurate classification.

Research team

Dr Ran Song

 

Outputs

Partners

Back to top
  • Facebook
  • Twitter
  • Instagram
  • TikTok
  • YouTube
  • LinkedIn icon

Contact us

University of Brighton
Mithras House
Lewes Road
Brighton
BN2 4AT

Main switchboard 01273 600900

Course enquiries

Sign up for updates

University contacts

Report a problem with this page

Quick links Quick links

  • Courses
  • Open days
  • Order a prospectus
  • Academic departments
  • Academic staff
  • Professional services departments
  • Jobs
  • Privacy and cookie policy
  • Accessibility statement
  • Libraries
  • Term dates
  • Maps
  • Graduation
  • Site information
  • Online shop
  • COVID-19

Information for Information for

  • Current students
  • International students
  • Media/press
  • Careers advisers/teachers
  • Parents/carers
  • Business/employers
  • Alumni/supporters
  • Suppliers
  • Local residents