Digital Image Inpainting using Speeded Up Robust Feature

被引:0
作者
Chavan, Trupti R. [1 ]
Nandedkar, Abhijeet V. [1 ]
机构
[1] SGGSIE&T, Elect & Telecommun Engn Dept, Vishnupuri 431606, Nanded, India
来源
2014 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATIONS AND INFORMATICS (ICACCI) | 2014年
关键词
Inpainting; region flling; SURF; affine transforms; relevant image; exemplar; scene completion; IMATRI;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
This paper focuses on the inpainting of damaged digital images. It uses relevant image and speeded-up robust features (SURF) for this purpose. A concept wherein, the missing information is restored using relevant image is presented. The relevant image may be a snapshot of the same location with different viewpoint or geometrical transformation. The proposed algorithm is divided into three main stages: Initially, key feature points of damaged and relevant image are found out. In second stage, the relation between the damaged and relevant image is found out in terms of affine transforms (i.e. scale, rotation and translation). Finally, the inverse transformation is applied to reconstruct the damaged area. PSNR is used to compare proposed method with the existing exemplar based method [4] and Hay's scene completion method [9]. The experimental results demonstrate that the proposed inpainting method is efficient in terms of quality and speed.
引用
收藏
页码:1408 / 1412
页数:5
相关论文
共 50 条
[21]   An efficient VLSI architecture of speeded-up robust feature extraction for high resolution and high frame rate video [J].
WeiLong Zhang ;
LeiBo Liu ;
ShouYi Yin ;
RenYan Zhou ;
ShanShan Cai ;
ShaoJun Wei .
Science China Information Sciences, 2013, 56 :1-14
[22]   An efficient VLSI architecture of speeded-up robust feature extraction for high resolution and high frame rate video [J].
ZHANG WeiLong ;
LIU LeiBo ;
YIN ShouYi ;
ZHOU RenYan ;
CAI ShanShan ;
WEI ShaoJun .
ScienceChina(InformationSciences), 2013, 56 (07) :136-149
[23]   An efficient VLSI architecture of speeded-up robust feature extraction for high resolution and high frame rate video [J].
Zhang WeiLong ;
Liu LeiBo ;
Yin ShouYi ;
Zhou RenYan ;
Cai ShanShan ;
Wei ShaoJun .
SCIENCE CHINA-INFORMATION SCIENCES, 2013, 56 (07) :1-14
[24]   An adaptive medical image registration using hybridization of teaching learning-based optimization with affine and speeded up robust features with projective transformation [J].
Arora, Paluck ;
Mehta, Rajesh ;
Ahuja, Rohit .
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2024, 27 (01) :607-627
[25]   An adaptive medical image registration using hybridization of teaching learning-based optimization with affine and speeded up robust features with projective transformation [J].
Paluck Arora ;
Rajesh Mehta ;
Rohit Ahuja .
Cluster Computing, 2024, 27 :607-627
[26]   Image Noise Removal using Image Inpainting [J].
Bakhtiari, Somayeh ;
Mohyedinbonab, Elmira ;
Agaian, Sos ;
Jamshidi, Mo .
IMAGE PROCESSING: ALGORITHMS AND SYSTEMS X AND PARALLEL PROCESSING FOR IMAGING APPLICATIONS II, 2012, 8295
[27]   SPEEDED-UP SURF: DESIGN OF AN EFFICIENT MULTISCALE FEATURE DETECTOR [J].
Schweiger, Florian ;
Schroth, Georg ;
Huitl, Robert ;
Latif, Yasir ;
Steinbach, Eckehard .
2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013), 2013, :3475-3478
[28]   Advance hybrid medical watermarking algorithm using speeded up robust features and discrete cosine transform [J].
Nawaz, Saqib Ali ;
Li, Jingbing ;
Bhatti, Uzair Aslam ;
Mehmood, Anum ;
Shoukat, Muhammad Usman ;
Bhatti, Mughair Aslam .
PLOS ONE, 2020, 15 (06)
[29]   Video Stabilization System Based on Speeded-up Robust Features [J].
Xie Zheng ;
Cui Shaohui ;
Wang Gang ;
Li Jinlun .
PROCEEDINGS OF THE 2015 INTERNATIONAL INDUSTRIAL INFORMATICS AND COMPUTER ENGINEERING CONFERENCE, 2015, :1995-1998
[30]   Multiple Pyramids Based Image Inpainting Using Local Patch Statistics and Steering Kernel Feature [J].
Ghorai, Mrinmoy ;
Samanta, Soumitra ;
Mandal, Sekhar ;
Chanda, Bhabatosh .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (11) :5495-5509