Name
Abstract | ||
|---|---|---|
With the flourish of multimedia on the web, it is easy to find similar images for a query, especially landmark images. Traditional image coding such as JPEG cannot exploit correlations with external images. Existing vision-based approaches by reconstructing from local descriptors are able to exploit such correlations but cannot ensure the pixel-level fidelity of the reconstruction. In this paper, a cloud-based distributed coding scheme (Cloud-DIC) is proposed to exploit external correlations for mobile photo uploading. For each input image, a thumbnail is transmitted to retrieve correlated images and reconstruct it in the cloud by geometrical and illumination registrations. Such a reconstruction serves as the side information (SI) in the Cloud- DIC. The image is then compressed by a transform-domain syndrome coding to correct the disparity between the original image and the SI. Once a bitplane is received in the cloud, an iterative refinement process is performed between the final reconstruction and the SI. Moreover, a joint encoder/decoder mode decision at block, frequency and bitplane levels is proposed to adapt to different correlations. Experiment results on a landmark image database show that the Cloud-DIC can largely enhance the coding efficiency both subjectively and objectively with up to 5dB gains and 70% bits saving over JPEG with arithmetic coding and perform comparably at low bit rates with HEVC intra coding with a much lower encoder complexity. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/TCSVT.2015.2416562 | Circuits and Systems for Video Technology, IEEE Transactions |
Keywords | Field | DocType |
cloud-based coding,distributed image coding,local feature descriptors | Computer vision,Image stitching,Automatic image annotation,Feature detection (computer vision),Pattern recognition,Computer science,Image texture,Image processing,Coding (social sciences),JPEG,Artificial intelligence,Cloud computing | Conference |
Volume | Issue | ISSN |
PP | 99 | 1051-8215 |
Citations | PageRank | References |
7 | 0.49 | 49 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiaodan Song | 1 | 733 | 54.42 |
| Xiaoyuan Peng | 2 | 28 | 4.16 |
| Xu, J. | 3 | 23 | 16.58 |
| Guangming Shi | 4 | 2663 | 184.81 |