We present a new nonparametric cooperative approach to multiband image segmentation. It is based on cooperation between region-growing segmentation and edge segmentation. This approach requires no input data other than the images to be processed. It uses a spectral homogeneity criterion whose threshold is determined automatically. The threshold is adaptive and varies depending on the objects to be segmented. Applying this new approach to very high resolution satellite imagery has yielded satisfactory results. The approach demonstrated its performance on images of varied complexity and was able to detect objects of great spatial and spectral heterogeneity.
© 2009 Optical Society of America
Original Manuscript: January 6, 2009
Revised Manuscript: June 1, 2009
Manuscript Accepted: June 3, 2009
Published: July 6, 2009
Imane Sebari and Dong-Chen He, "Approach to nonparametric cooperative multiband segmentation with adaptive threshold," Appl. Opt. 48, 3967-3978 (2009)