Title :
Snake in Phase Domain: A Method for Boundary Detection of Objects in Phase Images
Author :
Suksmono, Andriyan B. ; Handayani, Astri ; Hirose, Akira
Author_Institution :
Inst. Teknologi Bandung, Bandung
Abstract :
This paper presents a snake algorithm for boundary detection of objects in phase images. Since phase image is a modulo-2pi field, the proper gradient vector field (GVF) for snake dynamics should be taken from an unwrapped phase. This paper proposes a procedure to avoid such unwrapping by applying modulo-2pi gradient estimation. Performance assessment is conducted by comparing a boundary detection result of non-modulo-2pi GVF snake estimate with a modulo-2pi regularized GVF snake. It is shown that the proposed method converges to the expected boundary, while the non-regularized procedure does not.
Keywords :
edge detection; gradient methods; object detection; boundary object detection; gradient vector field; modulo-2pi field; modulo-2pi gradient estimation; phase domain; phase images; snake dynamics; unwrapped phase; Image converters; Image edge detection; Image processing; Image segmentation; Magnetic resonance imaging; Minimization methods; Object detection; Phase detection; Spline; Synthetic aperture radar interferometry; InSAR; MRI; energy minimization algorithm; gradient vector flow; modulo-2 regularization; phase image; phase unwrapping; snake algorithm;
Conference_Titel :
Neural Networks, 2006. IJCNN '06. International Joint Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-9490-9
DOI :
10.1109/IJCNN.2006.246720
