DocumentCode :
667289
Title :
Image registration of follow-up examinations in digital dermoscopy
Author :
Anagnostopoulos, Christos Nikolaos E. ; Vergados, Dimitrios D. ; Mintzias, Panagiotis
Author_Institution :
Cultural Technol. & Commun. Dept., Univ. of the Aegean, Lesvos, Greece
fYear :
2013
fDate :
10-13 Nov. 2013
Firstpage :
1
Lastpage :
4
Abstract :
Automated assessment tools for dermoscopy images play an important assistive role mainly due to inter- and intra-observer variations in human interpretation. Prior to classification, a robust registration module is necessary. In this paper we propose a fully automatic method for successful registration (matching) of melanocytic nevi images acquired from digital dermoscope to ensure reliable quantitative comparison of the image later. A modified SIFT algorithm (called ROI-SIFT), followed by RANSAC to identify outliers, is used to localize and match correspondence interest points, that will be used to compute affine transformations for the registration of a dermatological image with the respective follow-up examination image. Experimental evaluations of the registration method are reported for image pairs acquired during follow-up examinations. Finally, a short discussion of scheduled future work is proposed.
Keywords :
feature extraction; image matching; image registration; medical image processing; skin; RANSAC; ROI-SIFT algorithm; affine transformations; automated assessment tools; dermoscopy images; digital dermoscopy; follow-up examination image; image matching; image registration; inter-observer variations; intra-observer variations; melanocytic nevi image; random consensus sampling; regions-of-interest; robust registration module; scale-invariant feature transform; Data models; Hair; Image registration; Imaging; Lesions; Robustness; Skin;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Bioinformatics and Bioengineering (BIBE), 2013 IEEE 13th International Conference on
Conference_Location :
Chania
Type :
conf
DOI :
10.1109/BIBE.2013.6701627
Filename :
6701627
Link To Document :
بازگشت