Irmak, Hasan
Akar, Gözde
Yuksel, Seniha Esen
Hyperspectral imaging is widely used in many fields such as geology, medicine, meteorology, and so on. Despite the high spectral resolution, the spatial resolution of the hyperspectral sensors is severely limited. In this paper, we propose a novel maximum a posteriori (MAP)-based approach based on the joint superresolution of the abundance maps, to enhance the resolution of hyperspectral images. In the proposed approach, first, the endmembers and their abundance maps are estimated using Vertex Component Analysis (VCA) and Fully Constrained Least Squares (FCLS), respectively. Second, a high resolution (HR) abundance map is reconstructed for each low resolution (LR) abundance map using a MAP based approach. In the MAP-formulation data, smoothness and edge preservation constraints are extended to include a unity constraint term specific to abundances. Finally, HR hyperspectral images are reconstructed using the HR abundance maps. The proposed algorithm is tested on both synthetic images and real image sequences. The experimental results and comparative analysis verify the effectiveness of the proposed algorithm.


Deep CNN prior based image reconstruction for multispectral imaging
Manisali, İrfan; Cam, Refik; Bezek, Can Deniz; Öktem, Sevinç Figen (IEEE; 2020-10-07)
Spektral görüntüleme, fizik, kimya, biyoloji, tıp, astronomi ve uzaktan algılama gibi farklı alanlarda yaygın olarak kullanılan temel bir tanılayıcı tekniktir. Bu bildiride, hesaplamalı görüntüleme prensibine dayanan ve kırınımlı lens içeren birçoklu spektral görüntüleme tekniğine odaklanılmakta, bunun için evrişimsel sinir ağlarından yararlanan görüntü geriçatım yöntemi geliştirilmektedir. Sistemin elde ettiği ham verilerden spektral görüntülerin geriçatılması için, ters problem düzenlileştirme içeren bir ...
A pre-enactment model for measuring process quality
Güceğlioğlu, A. Selçuk; Demirörs, Onur; Department of Information Systems (2006)
Most of the process measurement studies are related with time and cost based models. Although quality is the other conventional aspect, there are no widely used models for measuring the process quality in the literature. In order to provide complementary information about the quality, a process quality measurement model has been chosen to be developed and the studies about process characteristics have been searched in the scope of the thesis. Moreover, by utilizing the similarities between process and softw...
Computational spectral imaging techniques using diffractive lenses and compressive sensing
Kar, Oğuzhan Fatih; Öktem, Sevinç Figen; Department of Electrical and Electronics Engineering (2019)
Spectral imaging is a fundamental diagnostic technique in physical sciences with application in diverse fields such as physics, chemistry, biology, medicine, astronomy, and remote sensing. In this thesis, we first present a modified version of a high-resolution computational spectral imaging modality and develop a fast sparse recovery method to solve the associated large-scale inverse problems. This technique uses a diffractive lens called photon sieve for dispersing the optical field. We then extend this t...
A Parametric Estimation Approach to Instantaneous Spectral Imaging
Öktem, Sevinç Figen; Davila, Joseph M (2014-12-01)
Spectral imaging, the simultaneous imaging and spectroscopy of a radiating scene, is a fundamental diagnostic technique in the physical sciences with widespread application. Due to the intrinsic limitation of two-dimensional (2D) detectors in capturing inherently three-dimensional (3D) data, spectral imaging techniques conventionally rely on a spatial or spectral scanning process, which renders them unsuitable for dynamic scenes. In this paper, we present a nonscanning (instantaneous) spectral imaging techn...
Computational Spectral Imaging with Photon Sieves
Öktem, Sevinç Figen; Davila, Joseph M. (2016-01-01)
Spectral imaging, the sensing of spatial information as a function of wavelength, is a widely used diagnostic technique in diverse fields such as physics, chemistry, biology, medicine, astronomy, and remote sensing. In this paper, we present a novel computational imaging modality that enables high-resolution spectral imaging by distributing the imaging task between a photon sieve system and a computer. The photon sieve system, coupled with a moving detector, provides measurements from multiple planes. Then ...
Citation Formats
H. Irmak, G. Akar, and S. E. Yuksel, “A MAP-BASED APPROACH TO RESOLUTION ENHANCEMENT OF HYPERSPECTRAL IMAGES,” 2015, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/54524.