Authors: Ferdinando Di Martino; Salvatore Sessa
Addresses: Dipartimento di Architettura, Università degli Studi di Napoli Federico II, Via Toledo 402, 80134 Napoli, Italy ' Dipartimento di Architettura, Università degli Studi di Napoli Federico II, Via Toledo 402, 80134 Napoli, Italy
Abstract: We present a new passive autofocusing algorithm based on fuzzy transforms. In a previous work (Roh et al., 2016) a localised variation of the variance operator is proposed based on the concept of fuzzy subspaces of the image: fuzzy C-means and conditional fuzzy C-means algorithms are applied for detecting the fuzzy subspaces as clusters. The direct fuzzy transform is used for extracting the mean values of the pixels in a fuzzy subspace. We propose a new approach based on the fuzzy generalised fuzzy C-means algorithm where the number of fuzzy subspaces is obtained by using the partition coefficient and exponential separation validity index. We show that the proposed method has major robustness with respect to other algorithms known in literature.
Keywords: image autofocusing; image contrast; variance; fuzzy C-means; FCM; fuzzy transform.
International Journal of Computational Science and Engineering, 2019 Vol.20 No.2, pp.240 - 254
Received: 21 Feb 2017
Accepted: 27 Sep 2017
Published online: 27 Nov 2019 *