Learning and Incorporating Top-Down Cues in Image Segmentation

2006 ◽  
pp. 338-351 ◽  
Author(s):  
Xuming He ◽  
Richard S. Zemel ◽  
Debajyoti Ray
Keyword(s):  
Image Segmentation ◽  
Top Down

A top-down region dividing approach for image segmentation

2008 ◽  
Vol 41 (6) ◽  
pp. 1948-1960 ◽  
Author(s):  
Yi-Ta Wu ◽  
Frank Y. Shih ◽  
Jiazheng Shi ◽  
Yih-Tyng Wu
Keyword(s):  
Image Segmentation ◽  
Top Down

A SELF-DIRECTED METHOD FOR IMAGE SEGMENTATION USING A MODIFIED TOP-DOWN REGION DIVIDING APPROACH

2014 ◽  
Vol 28 (06) ◽  
pp. 1455008
Author(s):  
WALTER S. WEHNER ◽  
FRANK Y. SHIH
Keyword(s):  
Image Segmentation ◽  
Computational Complexity ◽  
Standard Deviation ◽  
Spatial Structure ◽  
Region Growing ◽  
Connected Components ◽  
Segmentation Method ◽  
Top Down ◽  
Class Information ◽  
Structure Destruction

We present a self-directed method for image segmentation using a modified top-down region dividing (TDRD) approach. The TDRD-based image segmentation method solves some of the issues with histogram and region growing-based segmentation techniques. The process is efficient and achieves proper results without over segmentation or spatial-structure destruction. In this paper, we examine seven user-defined parameters of the method. These parameters are converted from human inputs to values derived from in-class information created by the algorithm allowing for autonomous image segmentation, without the need of human input or feedback. Our new autonomous implementation also reduces the computational complexity of the algorithm. This reduction will produce significant savings for the total number of computations the algorithm needs to perform image segmentation. Experimental results show that the images using these new derived values yield superior results as compared to other methods, including the original TDRD method. We compare our results visually and numerically based on the within-class standard deviation (WCSD) and the number of connected components (NCC).

Sign in / Sign up

Export Citation Format

Share Document