Proceedings Article10.1109/ICME.2012.52
SIFT-Based Image Compression
Huanjing Yue,Xiaoyan Sun,Feng Wu,Jingyu Yang +3 more
- 09 Jul 2012
- pp 473-478
31
TL;DR: A novel image compression scheme based on the local feature descriptor - Scale Invariant Feature Transform (SIFT) that provides a feasible approach to make use of the visual correlation among images.
read more
Abstract: This paper proposes a novel image compression scheme based on the local feature descriptor - Scale Invariant Feature Transform (SIFT). The SIFT descriptor characterizes an image region invariantly to scale and rotation. It is used widely in image retrieval. By using SIFT descriptors, our compression scheme is able to make use of external image contents to reduce visual redundancy among images. The proposed encoder compresses an input image by SIFT descriptors rather than pixel values. It separates the SIFT descriptors of the image into two groups, a visual description which is a significantly sub sampled image with key SIFT descriptors embedded and a set of differential SIFT descriptors, to reduce the coding bits. The corresponding decoder generates the SIFT descriptors from the visual description and the differential set. The SIFT descriptors are used in our SIFT-based matching to retrieve the candidate predictive patches from a large image dataset. These candidate patches are then integrated into the visual description, presenting the final reconstructed images. Our preliminary but promising results demonstrate the effectiveness of our proposed image coding scheme towards perceptual quality. Our proposed image compression scheme provides a feasible approach to make use of the visual correlation among images.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Landmark Image Super-Resolution by Retrieving Web Images
TL;DR: Experimental results demonstrate that the proposed new super-resolution (SR) scheme achieves significant improvement compared with four state-of-the-art schemes in terms of both subjective and objective qualities.
151
A novel approach for image compression based on multi-level image thresholding using Shannon Entropy and Differential Evolution
Sujoy Paul,Bitan Bandyopadhyay +1 more
- 01 May 2014
TL;DR: A histogram based image compression technique is proposed based on multi-level image thresholding based on Shannon's Entropy to reduce the computational time and standard deviation of optimized objective value.
49
PCA as Dimensionality Reduction for Large-Scale Image Retrieval Systems
TL;DR: Comparing multiple sets of data sets comparing dimensionality Reduction, Large-Scale Image Retrieval, Principal Component Analysis, Scale Invariant Feature Transform, Speeded Up Robust Features, and concluding that the PCA can beeffectively reduced.
43
Feature-based image set compression
Zhongbo Shi,Xiaoyan Sun,Feng Wu +2 more
- 15 Jul 2013
TL;DR: This paper is the first to propose a generic image set compression scheme which removes the set redundancy based on local features in addition to luminance values, and utilizes a SIFT-based global transformation to enhance the correlation between two images.
43
Feature Keypoint-Based Image Compression Technique Using a Well-Posed Nonlinear Fourth-Order PDE-Based Model
Tudor Barbu
- 07 Jun 2020
TL;DR: A digital image compression framework based on nonlinear partial differential equations (PDEs) based on feature keypoint-based sparsification algorithm for the image coding stage and an effective nonlinear fourth-order PDE-based scattered data interpolation for solving the decompression task.
9
References
Image Quality Measure Based On A Human Visual System Model
TL;DR: A preliminary image quality measure that takes into account two major sensitivities of the human visual system (HVS) is described and allows experimentation with numerous parameters of the HVS model to determine the optimum set for which the highest correlation with subjective evaluations can be achieved.
Edge-Oriented Uniform Intra Prediction
TL;DR: This paper considers the distinct image singularities within the model of piece-wise smooth functions and designs a rate-distortion optimized method for edge extraction and edge coding, which can be integrated into a block-based image coding scheme and achieves superior performance.
Scene completion using millions of photographs
James Hays,Alexei A. Efros +1 more
- 29 Jul 2007
TL;DR: A new image completion algorithm powered by a huge database of photographs gathered from the Web, requiring no annotations or labelling by the user, that can generate a diverse set of results for each input image and allow users to select among them.