|
Block-matching techniques have been widely used in the task of estimating displacement in medical images and
they stand for the best approach in scenes with deformable structures such as tissues, fluids or gels.
In this paper, a new iterative block-matching technique, based on successive deformation, search, fitting,
filtering and interpolation stages is proposed to measure elastic displacements in two dimensional
polyacrylamide gel electrophoresis images (2D-PAGE).
The proposed technique uses different deformation models in the task of correlating proteins in real 2D
electrophoresis gel images, obtaining an accuracy of 96.6% and improving the results obtained with other
techniques.
This technique stands for a general solution, being easy to adapt to different 2D deformable cases and providing
an experimental reference for block-matching algorithms.
|
.: SABIA :. Sistemas Adaptativos y Bioinspirados en Inteligencia Artificial