Title :
Elastic registration of gel electrophoresis images based on landmarks and intensities
Author :
Rohr, K. ; Cathier, P. ; Wörz, S.
Author_Institution :
Sch. of Inf. Technol., Int. Univ., Bruchsal, Germany
Abstract :
A key technique for protein analysis is the geometric alignment of gel electrophoresis images. While in previous work either intensity-based or landmark-based approaches have been used for the registration of electrophoresis images, we here introduce a scheme incorporating both intensities and landmarks. With this approach point landmarks are localized using a model fitting scheme and this geometric information is combined with intensity information for elastic registration. By experiments on the basis of images of different levels of complexity we demonstrate that intensity information alone is generally not sufficient for accurate registration. However, it turns out that the incorporation of landmarks significantly improves the registration accuracy.
Keywords :
biochemistry; biological techniques; biology computing; electrophoresis; image registration; molecular biophysics; proteins; elastic image registration; gel electrophoresis image; geometric alignment; intensity-based approach; landmark-based approach; protein analysis; Computer graphics; Computer vision; Electrokinetics; Image analysis; Image registration; Information analysis; Information technology; Proteins; Robustness; Solid modeling;
Conference_Titel :
Biomedical Imaging: Nano to Macro, 2004. IEEE International Symposium on
Print_ISBN :
0-7803-8388-5
DOI :
10.1109/ISBI.2004.1398822