Journal of Engineering and Applied Sciences
ISSN: Online 1818-7803ISSN: Print 1816-949x
Abstract
The computer vision is one of the most important specialties which can contribute on development of the computing. The estimation of the fundamental matrix remains a necessary tool to obtain and evaluate the relationships between two different view images. Different methods of segmentation exist to satisfy the specification of elimination of the false correspondence point. In this study, we propose a method based on the image segmentation using the super pixel algorithm. After that, we develop a new modification on the weighting function related with the fundamental matrix. Experimental comparisons were conducted through a simulation between the RANSAC, LMed, M-estimator and our method in order to estimate the projection error. Consequently, the proposed method gives a good performance results with a low error of projection compared to the others robust methods.
How to cite this article:
A. Chater and A. Lasfar. Detection of Image Descriptors and Modification of the Weighting Function for the
Estimation of the Fundamental Matrix Using Robust Methods.
DOI: https://doi.org/10.36478/jeasci.2018.1835.1843
URL: https://www.makhillpublications.co/view-article/1816-949x/jeasci.2018.1835.1843