Our work allows computers to recognize objects in images, what is distinctive about our work is that we also recover the 2D outline of the object.
Currently we have trained this model to recognize 20 classes. The demo below allows you to test our algorithm on your own images – have a try and see if you can fool it, if you get some good examples you can send them to us.
Why are we doing this? This work is part of a project to build augmented reality glasses for the partially sighted. Please read about it here smart-specs.
This demo is based on our ICCV 2015 paper Conditional Random Fields as Recurrent Neural Networks, which utilizes deep learning techniques and probabilistic graphical models for semantic image segmentation. [PDF] [Project] [Group] [Code] This demo website won best demo award in ICCV 2015.