Title :
A fast geometric active contour model with automatic region grid
Author :
Krishnan, N. ; Sujatha, S. Naga Nandini
Author_Institution :
Dept. of Inf. Technol., M. S. Univ., Thirunelveli, India
Abstract :
A new frame work for accurate extraction of object boundary from back ground for cell nucleus segmentation of cervical cancer images is proposed in this work. It proposes a new region grid algorithm for the fast evolution of level-set-based geometric active contours and compares it with other established numerical schemes. Geometric active contour models are very popular partial differential equation-based tools in object boundary extraction. This algorithm overcomes the drawback associated with the implementation of implicit schemes. The proposed system is more accurate compared with alternate split schemes. The region grid is formed by image gradient magnitude and directional information. The combined algorithm allows for the rapid evolution of the contour and convergence to its final configuration after very little iteration. The experiments demonstrate the efficiency and accuracy of the method.
Keywords :
cancer; cellular biophysics; computational geometry; feature extraction; gradient methods; image segmentation; medical image processing; partial differential equations; automatic region grid; back ground object boundary extraction; cell nucleus segmentation; cervical cancer image; fast geometric active contour model; image gradient magnitude; partial differential equation; Active contours; Convergence; Image edge detection; Image segmentation; Level set; Mathematical model; Minimization; Gradient magnitude; active contour segmentations; implicit and explicit schemes; level set;
Conference_Titel :
Computational Intelligence and Computing Research (ICCIC), 2010 IEEE International Conference on
Conference_Location :
Coimbatore
Print_ISBN :
978-1-4244-5965-0
Electronic_ISBN :
978-1-4244-5967-4
DOI :
10.1109/ICCIC.2010.5705794
