Olcay KURŞUN, Oleg FAVOROV

418436

SINGLE-FRAME SUPER-RESOLUTION BY INFERENCE FROM LEARNED FEATURES

SINGLE-FRAME SUPER-RESOLUTION BY INFERENCE FROM LEARNED FEATURES

Super-resolution is the creation of higher resolution views of pixel-based images through interpolation between the original pixels. Greater super-resolution can be achieved by taking advantage of local regularities inherent in natural images. In this paper, to learn regularities, we make use of the recently proposed SINBAD model  of how the cerebral cortical network learns regularities by discovering regularity-simplifying environmental features [5, 14]. Using the regularities discovered with the SINBAD approach, we were able to predict more accurately the interpolated pixels from the ones in the original image and were able to generate visually plausible fine spatial details in the expanded image
Keywords:

-,

PDF
Electrica-Cover
  • ISSN: 2619-9831
  • Yayın Aralığı: 3
  • Başlangıç: 2001
  • Yayıncı: İstanbul Üniversitesi-Cerrahpaşa
Arşiv
Sayıdaki Diğer Makaleler

SYNCHRONIZATION, CHAOS AND SPIKE PATTERNS IN NEOCORTICAL COMPUTATION

Ruedi STOOP, Daniel A. BLANK, Jan VYVER, Markus CHRISTEN, Albert KERN

A STUDY OF TRANSACTION CURTAILMENT MODEL BASED ON FUZZY SET THEORY

Hongming YANG, Xianzhong DUAN

GENERALIZED MODELING PRINCIPLES OF A NONLINEAR SYSTEM WITH A DYNAMIC FUZZY NETWORK

A.Ferit KONAR, Yusuf OYSAL

INTERPOLATION OF 2D SIGNALS USING CELLULAR NEURAL NETWORK

Alexandru GACSÁDI, Péter SZOLGAY

SINGLE-FRAME SUPER-RESOLUTION BY INFERENCE FROM LEARNED FEATURES

Olcay KURŞUN, Oleg FAVOROV

MODULAR AND HIERARCHICAL SPECIALIZATION IN NEURAL NETWORKS

A.J.W.M. ten BERG, L. SPAANENBURG

COMPUTATION OF RADIATION EFFICIENCY FOR A RESONANT RECTANGULAR MICROSTRIP PATCH ANTENNA USING BACKPROPAGATION MULTILAYERED PERCEPTRONS

Şeref SAĞIROĞLU, Kerim GÜNEY, Mehmet ERLER

FUZZY CONTROL SYSTEMS FOR THERMAL PROCESSES: SYNTHESIS, DESIGN AND IMPLEMENTATION

Lyupco N. ANTOVSKI, Mile J. STANKOVSKI, Tatyana D. K. GUGULOVSKA, Georgi M. DIMIROVSKI

A NEW RULE-BASED APPROACH FOR COMPUTER CHESS PROGRAMMING USING GP-ARTIFICIAL TECHNIQUES : PECP

Y.Güney HANEDAN, Ahmet SERTBAŞ

NEURAL NETWORK BASED DESIGN AND CONTROL OF ACOUSTO-OPTIC FILTER FIBRE-AMPLIFIER MODULE

Ömer MERMER, Gökalp KAHRAMAN, Musa ALCI