Please use this identifier to cite or link to this item:
標題: Detection and Segmentation of Cervical Cell Cytoplast and Nucleus
作者: Lin, C.H.
Chan, Y.K.
Chen, C.C.
關鍵字: cervical smear screening;level set;coarse;two-group;edge detection;thinning;active contour model;image segmentation;cortex
Project: International Journal of Imaging Systems and Technology
期刊/報告no:: International Journal of Imaging Systems and Technology, Volume 19, Issue 3, Page(s) 260-270.
This article alms to develop a method for the detection and segmentation of a cytoplast and nucleus from a cervix smear image. First, the technique of equalization method with Gaussian filter is adopted to eliminate noise in the image. Second. a new edge enhancement technique is proposed to work out the coarseness of each pixel, which is later used as a determining characteristic of reinforced object images. A two-group object enhancement technique is then used to reinforce this object according to rough pixels. Third, the proposed detector enhances the gradients of the edges of the cytoplast and nucleus while suppressing the noise gradients, and then specifies the pixels with higher gradients as possible edge pixels. Finally, it picks out the two longest closed curves constructed by part of the edge pixels. Detection and segmentation performance of the proposed method is later compared with seed region growing feature extraction and level set method using 10 cervix smear images as example. Besides comparing the contour segment of the cytoplast and nucleus obtained by using different methods, we also compare the quality of the segmentation results. Experimental results show that the proposed detector demonstrates an impressive performance. (C) 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 260-270, 2009 Published online in Wiley InterScience ( DOI 10.1002/ima.20198
ISSN: 0899-9457
DOI: 10.1002/ima.20198
Appears in Collections:資訊管理學系

Show full item record

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.