The one triangle three parallelograms sampling strategy and its application in shape regression
Author
Summary, in English
The purpose of this paper is threefold. Firstly, the paper introduces the One Triangle Three Parallelograms (OTTP) sampling strategy, which can be viewed as a way to index pixels from a given shape and image. Secondly, a framework for cascaded shape regression, including the OTTP sampling, is presented. In short, this framework involves binary pixel tests for appearance features combined with shape features followed by a large linear system for each regression stage in the cascade. The proposed solution is found to produce state-of-the-art results on the task of facial landmark estimation. Thirdly, the dependence of accuracy of the landmark predictions and the placement of the mean shape within the detection box is discussed and a method to visualize it is presented.
Department/s
- Mathematics (Faculty of Engineering)
- Mathematical Imaging Group
Publishing year
2016-02-17
Language
English
Pages
1538-1545
Publication/Series
Proceedings of the IEEE International Conference on Computer Vision
Document type
Conference paper
Publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
Topic
- Computer Vision and Robotics (Autonomous Systems)
Conference name
15th IEEE International Conference on Computer Vision, ICCV 2015
Conference date
2015-12-11 - 2015-12-18
Conference place
Santiago, Chile
Status
Published
Research group
- Mathematical Imaging Group
ISBN/ISSN/Other
- ISBN: 9781467383912