Object Detection by K-Connected Seed Competition

The notion of "strength of connectedness" between pixels has been successfully used in image segmentation. We present an extension to these works, which can considerably increase the efficiency of object definition tasks. A set of pixels is said a ê-connected component with respect to a se...

Full description

Saved in:
Bibliographic Details
Published inXVIII Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI'05) pp. 97 - 104
Main Authors Falcao, A.X., Miranda, P.A.V., Rocha, A., Bergo, F.P.G.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2005
Subjects
Automation
Biomedical imaging
Cost function
Image processing
Image segmentation
Joining processes
Object detection
Pixel
Online AccessGet full text

Cover

More Information
Summary:The notion of "strength of connectedness" between pixels has been successfully used in image segmentation. We present an extension to these works, which can considerably increase the efficiency of object definition tasks. A set of pixels is said a ê-connected component with respect to a seed pixel when the strength of connectedness of any pixel in that set with respect to the seed is higher than or equal to a threshold. While the previous approaches either assume no competition with a single threshold for all seeds or eliminate the threshold for seed competition, we found that seed competition with different thresholds can reduce the number of seeds and the need for user interaction during segmentation. We also propose automatic and user-friendly interactive methods for determining the thresholds. The improvements are demonstrated through several segmentation experiments involving medical images.
ISBN:9780769523897
0769523897
ISSN:1530-1834
2377-5416
DOI:10.1109/SIBGRAPI.2005.34