TY - GEN
T1 - Defocus Map Detection Using a Single Image
AU - Andrade, Juan
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2017/3/17
Y1 - 2017/3/17
N2 - The estimation of blurred regions is an important stage in several computer vision applications. In this paper an efficient training-free detector of local blurriness based on edge features is presented. Due to the intrinsic sparsity of edges in natural images a blur map is creating by using an approach based on the heat diffusion principle. A 2D point discrete Poisson solver is concatenated with a guided filter stage in order to create the blurring map. Experiments with images from two publicly available datasets validate the proposed method.
AB - The estimation of blurred regions is an important stage in several computer vision applications. In this paper an efficient training-free detector of local blurriness based on edge features is presented. Due to the intrinsic sparsity of edges in natural images a blur map is creating by using an approach based on the heat diffusion principle. A 2D point discrete Poisson solver is concatenated with a guided filter stage in order to create the blurring map. Experiments with images from two publicly available datasets validate the proposed method.
KW - blur map
KW - out of focus
KW - Poisson solver
UR - https://publicaciones.ucuenca.edu.ec/ojs/index.php/medicina/article/view/3012/2288
U2 - 10.1109/CSCI.2016.0151
DO - 10.1109/CSCI.2016.0151
M3 - Contribución a la conferencia
AN - SCOPUS:85017289320
T3 - Proceedings - 2016 International Conference on Computational Science and Computational Intelligence, CSCI 2016
SP - 777
EP - 780
BT - Proceedings - 2016 International Conference on Computational Science and Computational Intelligence, CSCI 2016
A2 - Yang, Mary
A2 - Arabnia, Hamid R.
A2 - Deligiannidis, Leonidas
A2 - Deligiannidis, Leonidas
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 International Conference on Computational Science and Computational Intelligence, CSCI 2016
Y2 - 15 December 2016 through 17 December 2016
ER -