Browsing by Author "Yildirim, Isa"

Now showing 1 - 3 of 3

Citation - WoS: 2
Implementation of Majorization-Minimization (MM) Algorithm for 3D Total Variation Minimization in DBT Image Reconstruction
(IEEE, 2016) Polat, Adem; Matela, Nuno; Mota, Ana Margarida; Yildirim, Isa
Digital Breast Tomosynthesis (DBT) is a developing imaging modality which produces 3D images of a breast. Iterative image reconstruction techniques, such as Algebraic reconstruction technique (ART), have been proposed to help increasing success in detecting masses and micro-calcifications. To enhance the quality of reconstructed image, total variation (TV) minimization was applied to the images reconstructed by ART. Nowadays, the number of published papers dealing with 3D TV minimization on ART (ART+TV3D) tends to increase. On the other hand, in the signal processing literature, a new majorization-minimization (MM) algorithm on TV denoising is described for an N-point x(n) as 1D signal. According to our literature review, this 1D MM algorithm has not been applied to DBT studies yet. In this paper, we propose a method to combine MM1D algorithm with ART+TV3D: "ART+TV3D+MM1D". Both quantitative and qualitative analyses of the proposed method ART+TV3D+MM1D, ART+TV3D, and ART are performed for a phantom that mimics 3D breast and a real 3D breast phantom with 301x236x8-dimensions.
Citation - WoS: 12
Citation - Scopus: 19
An Approximate Spectral Clustering Ensemble for High Spatial Resolution Remote-Sensing Images
(IEEE-Inst Electrical Electronics Engineers Inc, 2015) Tasdemir, Kadim; Moazzen, Yaser; Yildirim, Isa
Unsupervised clustering of high spatial resolution remote-sensing images plays a significant role in detailed land-cover identification, especially for agricultural and environmental monitoring. A recently promising method is approximate spectral clustering (SC) which enables spectral partitioning for large datasets to extract clusters with distinct characteristics without a parametric model. It also facilitates the use of various information types via advanced similarity criteria. However, it requires an empirical selection of a similarity criterion optimal for the corresponding application. To address this challenge, we propose an approximate SC ensemble (ASCE2) which fuses partitionings obtained by different similarity representations. Contrary to existing spectral ensembles for remote-sensing applications, the proposed ASCE2 employs neural gas quantization instead of random sampling, advanced similarity criteria instead of traditional distance-based Gaussian kernel with different decay parameters, and a two-level ensemble. We evaluate the proposed ASCE2 with three measures (accuracy, adjusted Rand index, and normalized mutual information) using five remote-sensing images, two of which are commonly available. We apply the ASCE2 in two applications for agricultural monitoring: 1) land-cover identification to determine orchard fields using a WorldView-2 image (0.5-m spatial resolution) and 2) finding lands in good agricultural condition using multitemporal RapidEye images (5-m spatial resolution). Experimental results indicate a significant betterment of the resulting partitionings obtained by the proposed ensemble, with respect to the evaluation measures in these applications.
Citation - WoS: 14
Citation - Scopus: 13
Iterative Image Reconstruction Using Non-Local Means With Total Variation From Insufficient Projection Data
(Ios Press, 2016) Ertas, Metin; Yildirim, Isa; Kamasak, Mustafa; Akan, Aydin
In this work, algebraic reconstruction technique (ART) is extended by using non-local means (NLM) and total variation (TV) for reduction of artifacts that are due to insufficient projection data. TV and NLM algorithms use different image models and their application in tandem becomes a powerful denoising method that reduces erroneous variations in the image while preserving edges and details. Simulations were performed on a widely used 2D Shepp-Logan phantom to demonstrate performance of the introduced method (ART + TV) NLM and compare it to TV based ART (ART + TV) and ART. The results indicate that (ART + TV) NLM achieves better reconstructions compared to (ART + TV) and ART.