A Rigid Point Set Registration of Remote Sensing Images Based On Genetic Algorithms & Hausdorff Distance

F. Meskine (1) , Nasreddine Taleb (1) , Miloud Chikr El-Mezouar (2) , Kidiyo Kpalma (2) , Ahmad Almhdie (3)

1 UDL - جامعة جيلالي اليابس [سيدي بلعباس، الجزائر] = Université Djillali Liabès [Sidi Bel Abbès, Algérie] = Djillali Liabes University [Sidi Bel Abbès, Algeria]
2 IETR - Institut d'Électronique et des Technologies du numéRique
3 ISTO - Institut des Sciences de la Terre d'Orléans - UMR7327

Image registration is the process of establishing point by point correspondence between images obtained from a same scene. This process is very useful in remote sensing, medicine, cartography, computer vision, etc. Then, the task of registration is to place the data into a common reference frame by estimating the transformations between the data sets. In this work, we develop a rigid point registration method based on the application of genetic algorithms and Hausdorff distance. First, we extract the feature points from both images based on the algorithm of global and local curvature corner. After refining the feature points, we use Hausdorff distance as similarity measure between the two data sets and for optimizing the search space we use genetic algorithms to achieve high computation speed for its inertial parallel. The results show the efficiency of this method for registration of satellite images.

Mots clés: Feature extraction; Genetic algorithms; Hausdorff distance; Image registration; Point registration.; Point registration

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

F. Meskine, Nasreddine Taleb, Miloud Chikr El-Mezouar, Kidiyo Kpalma, Ahmad Almhdie. A Rigid Point Set Registration of Remote Sensing Images Based On Genetic Algorithms & Hausdorff Distance. World Academy of Science, Engineering and Technology, 2013, pp.1095-1100. ⟨hal-00870232⟩