Thesis
From interactive to semantic image segmentation
- Abstract:
-
This thesis investigates two well defined problems in image segmentation, viz. interactive and semantic image segmentation. Interactive segmentation involves power assisting a user in cutting out objects from an image, whereas semantic segmentation involves partitioning pixels in an image into object categories. We investigate various models and energy formulations for both these problems in this thesis.
In order to improve the performance of interactive systems, low level texture fe...
Expand abstract
Actions
Authors
Contributors
+ Zisserman, A
- Division:
- MPLS
- Department:
- Engineering Science
- Role:
- Supervisor
+ Blake, A
- Division:
- MPLS
- Department:
- Engineering Science
- Role:
- Supervisor
+ Microsoft Research, UKIERI, ERC, RAEng
More from this funder
- Funding agency for:
- Gulshan, V
- Grant:
- ERC grant VisRec No. 228180
- Publication date:
- 2011
- Type of award:
- DPhil
- Level of award:
- Doctoral
- Awarding institution:
- Oxford University, UK
- Language:
-
English
- Keywords:
- Subjects:
- UUID:
-
uuid:706b648a-e5e7-4334-a456-0f0b5701dbc4
- Local pid:
-
ora:6113
- Deposit date:
-
2012-03-08
Terms of use
- Copyright holder:
- Gulshan, V
- Copyright date:
- 2012
If you are the owner of this record, you can report an update to it here: Report update to this record