A Novel Unsup ervised Two-Stage Technique in Color Image Segmentation

摘要

A new unsupervised two-stage method for color image segmentation is proposed. The method con-tains coarse segmentation and delicate segmentation. In coarse segmentation, we adaptively choose a gray channel from CIE-lab color space. The Otsu method combined with a refinement to its threshold is applied to get global opti-mal segmentation. In delicate segmentation, a narrowband based procedure is applied to get more accurate contour of the object and local optimal segmentation is achieved. Our method finally balance the global optimal and the local op-timal. The proposed method does not need initial contours or initial labels, thus it is more robust in certain applica-tions. Experimental results of our method in MSRA1000 database show that our method is robust in segmenting objects and backgrounds when possessing weakly hetero-geneous color. Our method firstly achieves global optimal and then achieves local optimal which draws a new and prospective outlook for segmenting color images.