A Bayesian nonparametric model for hierarchical sequence of images
Version 2 2024-06-17, 13:14Version 2 2024-06-17, 13:14
Version 1 2015-03-09, 23:25Version 1 2015-03-09, 23:25
conference contribution
posted on 2024-06-17, 13:14authored byY Qiu, X Sun, MF She
Scale features are useful for a great number of applications in computer vision. However, it is difficult to tolerate diversities of features in natural scenes by parametric methods. Empirical studies show that object frequencies and segment sizes follow the power law distributions which are well generated by Pitman-Yor (PY) processes. Based on mid-level segments, we propose a hierarchical sequence of images to obtain scale information stored in a hierarchical structure through the hierarchical Pitman-Yor (HPY) model which is expected to tolerate uncertainty of natural images. We also evaluate our representation by the application of segmentation.
History
Pagination
1-6
Location
Hangzhou City, China
Start date
2014-10-18
End date
2014-10-19
Language
eng
Publication classification
E Conference publication, E1 Full written paper - refereed
Copyright notice
2014, DEStech Publications
Editor/Contributor(s)
[Unknown]
Title of proceedings
CSSE 2014 : Proceedings of the 2014 International Conference on Computer Science and Software Engineering
Event
Computer Science and Software Engineering. Conference ( 2014: Hangzhou City, China)