TITLE

OBTAINING SUPER-RESOLUTION IMAGES BY COMBINING LOW-RESOLUTION IMAGES WITH HIGH-FREQUENCY INFORMATION DERIVEDFROM TRAINING IMAGES

AUTHOR(S)
Bilgazyev, Emil; Tsekos, Nikolaos; Leiss, Ernst
PUB. DATE
April 2013
SOURCE
International Journal of Computer Science & Information Technolo;Apr2013, Vol. 5 Issue 2, p19
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
In this paper, we propose a new algorithm to estimate a super-resolution image from a given low-resolution image, by adding high-frequency information that is extracted from natural high-resolution images in the training dataset. The selection of the high-frequency information from the training dataset is accomplished in two steps, a nearest-neighbor search algorithm is used to select the closest images from the training dataset, which can be implemented in the GPU, and a sparse-representation algorithm is used to estimate a weight parameter to combine the high-frequency information of selected images. This simple but very powerful super-resolution algorithm can produce state-of-the-art results. Qualitatively and quantitatively, we demonstrate that the proposed algorithm outperforms existing state-of-the-art super-resolution algorithms.
ACCESSION #
88086425

 

Related Articles

  • Enhancing the Performance of GPU for Face Detection. Faheem, Hossam M.; Ghoniemy, S.; Abdelaal, T. A. Yara M. // International Journal of Computer Applications;May2014, Vol. 94, p25 

    Computer Vision algorithms are considered computationally intensive problems. Face detection is one of the most complex objects to detect due to its variations. The objective is to enhance the face detection time (compared with other approaches) to reach a real-time application that will be...

  • A Cooperativ e Dual-camera System for Face Recognition and Video Monitoring. Zhuo Chen; Haibo Wu; Shengping Xia // Advanced Materials Research;2014, Vol. 998-999, p784 

    In the ordinary video monitoring system, the whole small scene is usually observed by a stationary camera or a few stationary cameras, but the system can't zoom and focus on the target of interest rapidly, and also can't get the high resolution image of the target of interest in a far distance....

  • A two-step face hallucination approach for video surveillance applications. Jia, Zhen; Zhao, Jianwei; Wang, Hongcheng; Xiong, Ziyou; Finn, Alan // Multimedia Tools & Applications;Mar2015, Vol. 74 Issue 6, p1845 

    In this paper we propose a novel face hallucination algorithm to synthesize a high-resolution face image from several low-resolution input face images. Face hallucination normally uses two models: a global parametric model which synthesizes the global face shapes from eigenfaces, and a local...

  • Face Recognition using SIFT Descriptor under Multiple Paradigms of Graph Similarity Constraints. Kisku, Dakshina Ranjan; Gupta, Phalguni; Sing, Jamuna Kanta // International Journal of Multimedia & Ubiquitous Engineering;2010, Vol. 5 Issue 4, p1 

    Biometric systems are considered as human pattern recognition systems that can be used for individual identification and verification. The decision on the authenticity is done with the help of some specific measurable physiological or behavioral characteristics possessed by the individuals....

  • A New Multi Fractal Dimension Method for Face Recognition with Fewer Features under Expression Variations. Ahamad, Maksud; Shahid, Saman // International Journal on Computer Science & Engineering;Jun2012, Vol. 4 Issue 6, p1086 

    In this work, a new method is presented as a mingle of Principal Component Analysis (PCA) and Multi-Fractal Dimension analysis (MFD) for feature extraction. Proposed method makes use of best decision taken from both the methods and make use of fewer and effective features than traditional...

  • Extraction of Facial Feature Points Using Cumulative Histogram. Paul, Sushil Kumar; Uddin, Mohammad Shorif; Bouakaz, Saida // International Journal of Computer Science Issues (IJCSI);Jan2012, Vol. 9 Issue 1, p44 

    This paper proposes a novel adaptive algorithm to extract facial feature points automatically such as eyebrows corners, eyes corners, nostrils, nose tip, and mouth corners in frontal view faces, which is based on cumulative histogram approach by varying different threshold values. At first, the...

  • Using Implicit Shape Model and SVM for Face Detection. Zhi-Kai Huang; Ling-Ying Hou; Xing-Wang Zhang; Jing-Jing Lian // International Journal of Advancements in Computing Technology;Dec2011, Vol. 3 Issue 11, p130 

    This paper proposes a new framework for face detection based on Implicit Shape Model (ISM) support vector machine classifier. At first, some sample points in the image using Harris interest point detector have been extracted and compute local Histograms of Oriented Gradients (HoG) feature of...

  • Efficient model building in active appearance model for rotated face. Jaehyun So; Sanghun Han; Youngtak Kim; Hwanik Chung; Youngjoon Han // Journal of Measurement Science & Instrumentation;Dec2013, Vol. 4 Issue 4, p346 

    This paper proposes the efficient model building in active appearance model (AAM) for the rotated face. Finding an exact region of the face is generally difficult due to different shapes and viewpoints. Unlike many papers about the fitting method of AAM, this paper treats how images are chosen...

  • Digital Information Facial Recognition Based on PCA and Its Improved Algorithm. Hai-feng Zhu // Journal of Digital Information Management;Oct2013, Vol. 11 Issue 5, p390 

    Face recognition (PCA algorithm) based on principal component analysis method is a classic algorithm of digital information face recognition. This paper first analyzes the PCA algorithm and its basic principles. And in view of the shortage that it is affected by its subject facial expression...

Share

Read the Article

Courtesy of VIRGINIA BEACH PUBLIC LIBRARY AND SYSTEM

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics