Abstract                                                

Image registration is an important problem for image processing and computer vision with many proposed applications in medical image analysis. Image registration techniques attempt to map corresponding features between two images. In this paper we propose an approach for medical images registration characterized by their great heterogeneity and complexity. It is carried out through the extraction of interest regions or points of the both images source and destination. The correlation technique ZNCC (Zero mean Normalized Cross Correlation) combined with relaxation is used for matching the interest points. In region based registration approach, the image segmentation involves growing regions from individual pixels using a stack-based approach. The matching between the extracted regions is established with a new descriptor that involves three parameters: color, position, and shape. The shape is characterized by the invariant geometrical moment. The least means square is used to estimate the registration parameters. The whole results obtained are rather satisfactory and very encouraging.

Keywords: registration, medical imagery, interest points, interest regions, matching.

(P1150724001, 1.06 MB)

Biographies:

	Ghizlane Khaissidi, received his Master’s degree in 2004 from faculty of sciences and techniques (FST) Fes MORROCO. She is pursuing her Ph.D. degree. Her doctoral study focused on registration and fusion in medical imagery.
	Mohamed Karoud, received his Master’s degree in 2004 from the University Sidi Mohamed Ben Abdellah, Morocco Morocco. He is pursuing his Ph.D. degree. His doctoral study focused on registration and fusion in medical imagery.
	Hamid Tairi, received his PhD degree in 2001 from the University Sidi Mohamed Ben Abdellah, Morocco. In 2002 he has done a postdoc in the Image Processing Group of the Laboratory LE2I (Laboratoire d’Electronique, Informatique et Image).  Since 2003, he has been an associate professor at the University Sidi Mohamed Ben Abdellah, Morocco. His research interests are in visual tracking for robotic control, in 3-D reconstruction of artificial vision, in medical image, in visual information retrieval and pattern recognition.
	Abdellah Aarab, is Professor at the Faculty of Sciences, Fes Morocco. He received his "Doctorat de 3ième cycle" degree from the University of Pau, France in 1982 and "Thèse d'Etat" degree in 1999 from university Sidi Mohamed Ben Abdellah Fes Morocco. His research areas include, image processing, information retrieval and industrial applications.

BibTex:

@ARTICLE{P1150724001,

AUTHOR = {G. Khaissidi and M. Karoud and H. Tairi and A. Aarab },

TITLE = {Medical Image Registration using Regions Matching with Invariant Geometrical Moments},

JOURNAL ={ICGST International Journal on Graphics, Vision and Image Processing, GVIP},

YEAR = {2008},

VOLUME = {08},

ISSUE ={II},

PAGES={15--20}

}

(P1150724001, 1.06 MB)