Universal image coding approach using sparse steered Mixture-of-Experts regression
- Author
- Ruben Verhack, Thomas Sikora, Lieven Lange, Glenn Van Wallendael (UGent) and Peter Lambert (UGent)
- Organization
- Abstract
- Our challenge is the design of a "universal" bit-efficient image compression approach. The prime goal is to allow reconstruction of images with high quality. In addition, we attempt to design the coder and decoder "universal", such that MPEG-7-like low-and mid-level descriptors are an integral part of the coded representation. To this end, we introduce a sparse Mixture-of-Experts regression approach for coding images in the pixel domain The underlying stochastic process of the pixel amplitudes are modelled as a 3-dimensional and multi-modal Mixture-of-Gaussians with K modes. This closed form continuous analytical model is estimated using the Expectation-Maximization algorithm and describes segments of pixels by local 3-D Gaussian steering kernels with global support. As such, each component in the mixture of experts steers along the direction of highest correlation. The conditional density then serves as the regression function. Experiments show that a considerable compression gain is achievable compared to JPEG for low bitrates for a large class of images, while forming attractive low-level descriptors for the image, such as the local segmentation boundaries, direction of intensity flow and the distribution of these parameters over the image
- Keywords
- Mixture of Experts, Gaussian Mixture Regression, Steering Regression, Gaussian Mixture Models, Sparse Image Coding
Downloads
-
2016 - Ruben Verhack et al. - A universal image coding approach using sparse steered Mixture-of-Experts regression.pdf
- full text
- |
- open access
- |
- |
- 589.10 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8504375
- MLA
- Verhack, Ruben, et al. “Universal Image Coding Approach Using Sparse Steered Mixture-of-Experts Regression.” 2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), Institute of Electrical and Electronics Engineers (IEEE), 2016, pp. 2142–46, doi:10.1109/icip.2016.7532737.
- APA
- Verhack, R., Sikora, T., Lange, L., Van Wallendael, G., & Lambert, P. (2016). Universal image coding approach using sparse steered Mixture-of-Experts regression. 2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2142–2146. https://doi.org/10.1109/icip.2016.7532737
- Chicago author-date
- Verhack, Ruben, Thomas Sikora, Lieven Lange, Glenn Van Wallendael, and Peter Lambert. 2016. “Universal Image Coding Approach Using Sparse Steered Mixture-of-Experts Regression.” In 2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2142–46. Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/icip.2016.7532737.
- Chicago author-date (all authors)
- Verhack, Ruben, Thomas Sikora, Lieven Lange, Glenn Van Wallendael, and Peter Lambert. 2016. “Universal Image Coding Approach Using Sparse Steered Mixture-of-Experts Regression.” In 2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2142–2146. Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/icip.2016.7532737.
- Vancouver
- 1.Verhack R, Sikora T, Lange L, Van Wallendael G, Lambert P. Universal image coding approach using sparse steered Mixture-of-Experts regression. In: 2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP). Institute of Electrical and Electronics Engineers (IEEE); 2016. p. 2142–6.
- IEEE
- [1]R. Verhack, T. Sikora, L. Lange, G. Van Wallendael, and P. Lambert, “Universal image coding approach using sparse steered Mixture-of-Experts regression,” in 2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), Phoenix, AZ, USA, 2016, pp. 2142–2146.
@inproceedings{8504375,
abstract = {{Our challenge is the design of a "universal" bit-efficient image compression approach. The prime goal is to allow reconstruction of images with high quality. In addition, we attempt to design the coder and decoder "universal", such that MPEG-7-like low-and mid-level descriptors are an integral part of the coded representation. To this end, we introduce a sparse Mixture-of-Experts regression approach for coding images in the pixel domain The underlying stochastic process of the pixel amplitudes are modelled as a 3-dimensional and multi-modal Mixture-of-Gaussians with K modes. This closed form continuous analytical model is estimated using the Expectation-Maximization algorithm and describes segments of pixels by local 3-D Gaussian steering kernels with global support. As such, each component in the mixture of experts steers along the direction of highest correlation. The conditional density then serves as the regression function. Experiments show that a considerable compression gain is achievable compared to JPEG for low bitrates for a large class of images, while forming attractive low-level descriptors for the image, such as the local segmentation boundaries, direction of intensity flow and the distribution of these parameters over the image}},
author = {{Verhack, Ruben and Sikora, Thomas and Lange, Lieven and Van Wallendael, Glenn and Lambert, Peter}},
booktitle = {{2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)}},
isbn = {{978-1-4673-9961-6}},
issn = {{1522-4880}},
keywords = {{Mixture of Experts,Gaussian Mixture Regression,Steering Regression,Gaussian Mixture Models,Sparse Image Coding}},
language = {{eng}},
location = {{Phoenix, AZ, USA}},
pages = {{2142--2146}},
publisher = {{Institute of Electrical and Electronics Engineers (IEEE)}},
title = {{Universal image coding approach using sparse steered Mixture-of-Experts regression}},
url = {{http://doi.org/10.1109/icip.2016.7532737}},
year = {{2016}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: