Abstract
This paper describes detection of distorted frames in retinal sequences based on set of global features extracted from each frame. The feature vector is consequently used in classification step, in which three types of classifiers are tested. The best classification accuracy 96% has been achieved with support vector machine approach.
© 2017 SPIE
PDF ArticleMore Like This
Travis B. Smith and Ning Smith
JTu5A.41 Computational Optical Sensing and Imaging (COSI) 2014
Ralf P. Tornow, Aleksandra Milczarek, Jan Odstrcilik, and Radim Kolar
1041309 European Conference on Biomedical Optics (ECBO) 2017
Ralf P. Tornow, Radim Kolář, and Jan Odstrčilík
954006 European Conference on Biomedical Optics (ECBO) 2015