Projecting Active Contours with Diminutive Sequence Optimality
Keywords:
Abstract
Active contours are widely used in image segmentation. To cope with missing or misleading features in image frames taken in contexts such as spatial and surveillance, researchers have commence various ways to model the preceding of shapes and use the prior to constrict active contours. However, the shape prior is frequently learnt from a large set of annotated data, which is not constantly accessible in practice. In addition, it is often doubted that the existing shapes in the training set will be sufficient to model the new instance in the testing image. In this paper we propose to use the diminutive sequence of image frames to learn the missing contour of the input images. The central median minimization is a simple and effective way to impose the proposed constraint on existing active contour models. Moreover, we extend a fast algorithm to solve the projected model by using the hastened proximal method. The Experiments done using image frames acquired from surveillance, which demonstrated that the proposed method can consistently improve the performance of active contour models and increase the robustness against image defects such as missing boundaries.
Downloads
- Article PDF
- TEI XML Kaleidoscope (download in zip)* (Beta by AI)
- Lens* NISO JATS XML (Beta by AI)
- HTML Kaleidoscope* (Beta by AI)
- DBK XML Kaleidoscope (download in zip)* (Beta by AI)
- LaTeX pdf Kaleidoscope* (Beta by AI)
- EPUB Kaleidoscope* (Beta by AI)
- MD Kaleidoscope* (Beta by AI)
- FO Kaleidoscope* (Beta by AI)
- BIB Kaleidoscope* (Beta by AI)
- LaTeX Kaleidoscope* (Beta by AI)
How to Cite
Published
2013-07-15
Issue
Section
License
Copyright (c) 2013 Authors and Global Journals Private Limited
This work is licensed under a Creative Commons Attribution 4.0 International License.