2-D Electrophoresis Gel Registration using Feature Matching

M Rogers, J Graham and R P Tonge, "2-D Electrophoresis Gel Registration using Feature Matching", Proceedings of the IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp 1436-1439, 2004. PDF | IEEE Xplore


We have carried out an evaluation of feature matching algorithms and developed an automatic method of 2-D Electrophoresis gel registration. We show that bi-partite graph matching is not appropriate in this context, and have used a combination of shape context and euclidian distance measures together with closest point correspondence estimation in our scheme. Our final algorithm is shown to be more robust than a recently published image intensity based method.