Fast Edge-preserving Gravity-like Image Interpolation

被引：0
作者：
Lukac, Zeljko [1 ,4 ]
Ocovaj, Stanislav [1 ,3 ,4 ]
Samardzija, Dragan [2 ,3 ]
Temerinac, Miodrag [3 ]
机构：
[1] RT RK Inst Comp Based Syst, Narodnog Fronta 23a, Novi Sad 21000, Serbia
[2] Nokia Bell Labs, 101 Crawfords Corner Rd, Holmdel, NJ USA
[3] Univ Novi Sad, Fac Tech Sci, Trg Dositeja Obradov 6, Novi Sad 21000, Serbia
[4] Fac Tech Sci, Comp Engn & Comp Commun, Novi Sad, Serbia
来源：
COMPUTER SCIENCE AND INFORMATION SYSTEMS | 2017年 / 14卷 / 01期
关键词：
edge directed interpolation; edge preservation; image interpolation; image processing; ALGORITHM;
D O I：
10.2298/CSIS151225041L
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper we propose a novel image interpolation algorithm which preserves edges and keeps a natural texture of interpolated images. The algorithm is based on an idea that only pixels that belong to the same side of an edge should be used in interpolation of pixels that belong to an edge. Beside similarity-based separation of known interpolation pixels a gravity-like interpolation coefficient set is also introduced in order to support different number of interpolation pixels and their location in two dimensional plane. The algorithm also applies arbitrary scaling factors, thus offering a broader scope of applications. Use of a local set of interpolating points makes the proposed algorithm suitable for applications on resource-limited platforms. The edge performance is demonstrated for structured geometric forms, while a general interpolated image quality is evaluated using objective measures and subjective comparisons. A comparison with some relevant interpolation algorithms shows the desirable tradeoff between image quality (sharpness and texture) and requested computing power (run-time).
引用
收藏
页码：153 / 173
页数：21
相关论文
共 33 条
[1]  
Amanatiadis A., 2009, MEASUREMENT SCI TECH, V20, P1
[2]   Performance Evaluation Techniques for Image Scaling Algorithms [J].
Amanatiadis, Angelos ;
Andreadis, Ioannis .
2008 IEEE INTERNATIONAL WORKSHOP ON IMAGING SYSTEMS AND TECHNIQUES, 2008, :114-118
[3]   A locally adaptive zooming algorithm for digital images [J].
Battiato, S ;
Gallo, G ;
Stanco, F .
IMAGE AND VISION COMPUTING, 2002, 20 (11) :805-812
[4]  
Battiato S., 2007, Proc. IEEE Int. Conf. Consumer Electron, P1
[5]   Linear interpolation revitalized [J].
Blu, T ;
Thévenaz, P ;
Unser, M .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2004, 13 (05) :710-719
[6]  
Carrato S, 1996, INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, PROCEEDINGS - VOL III, P711, DOI 10.1109/ICIP.1996.560778
[7]  
Dong C., 2015, Matlab demo code for "Learning a Deep Convolutional Network for Image Super-Resolution" and "Image Super-Resolution Using Deep Convolutional Networks"
[8]   Image Super-Resolution Using Deep Convolutional Networks [J].
Dong, Chao ;
Loy, Chen Change ;
He, Kaiming ;
Tang, Xiaoou .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (02) :295-307
[9]   Learning a Deep Convolutional Network for Image Super-Resolution [J].
Dong, Chao ;
Loy, Chen Change ;
He, Kaiming ;
Tang, Xiaoou .
COMPUTER VISION - ECCV 2014, PT IV, 2014, 8692 :184-199
[10]   Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization [J].
Dong, Weisheng ;
Zhang, Lei ;
Shi, Guangming ;
Wu, Xiaolin .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2011, 20 (07) :1838-1857
1234