Department of Computer Science and Engineering
University of Washington
This research was partially funded by a gift from the Adobe Corporation.
This work is about the precurser to object recognition: object proposals.
The idea is to find regions in images that are likely to contain objects.
Then these regions can be fed into classifiers for recognition.
Image Segmentation for Camera Phones
*This research is in collaboration with and funded by a gift from
Among the many problems in image editing, cutting out an
object is a very important task. Directly applying algorithms
targeted for desktops to mobile phones does not yield
the desired performance and user experience. This project
supports the development of interactive, real-time algorithms
for mobile phone image segmentation.
- PI: Linda Shapiro (UW)
- Nokia Collaborators: Yingen Xiong and Kari Pulli
- Student: Dingding (Dee) Liu
D. Liu, Y. Xiong, K. Pulli, L. Shapiro,
"Estimating Image Segmentation Difficulty,"
International Conference on Machine Learning and Data Mining,
D. Liu, K. Pulli, L. Shapiro, Y. Xiong,
"Fast Interactive Image Segmentation by Discriminative Clustering,"
First ACM International Workshop on Mobile Cloud Media
- D. Liu, Y. Xiong, L. Shapiro, K. Pulli,
"Robust Interactive Image Segmentation with Automatic
IEEE International Conference on Image Processing, 2010.
- Y. Xiong, D. Liu, K. Pulli,
"Effective Gradient Domain Object Editing on Mobile Devices,"
IEEE 43rd Asilomar Conference on Signals, Systems, and