Ledeberg, Belgium
Ledeberg, Belgium

Time filter

Source Type

Gaj S.,Multimedia Laboratory | Rana S.,Multimedia Laboratory | Sur A.,Multimedia Laboratory | Bora P.K.,Indian Institute of Technology Guwahati
2016 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2016 | Year: 2016

Camcorder based video copy attack has become a serious threat to the electronic movie distribution services. In literature, it is found that main distortions caused during cam-cording are frame blending and projection attacks. Though, several watermarking schemes exist to handle geometric distortions caused during cam-cording, very few of them are robust against temporal distortion. Based on the existing limitations of the state-of-art literature, a blind watermarking scheme which is robust against both frame blending and projection attacks is proposed in this paper. Using scale invariant feature transform (SIFT) and higher-order singular value decomposition (HOSVD), the temporal synchronization between cam-corded video and source video is achieved. Further, SIFT and log-polar transform are used together to achieve spatial synchronization of the embedding locations. The main contribution of this work is twofold, primarily it handles the frame blending and projection attacks during cam-cording and secondly it prevents the distortion in the watermark signal when different content adaptation is done specially when the quality and temporal adaptation is done in case of scalable video. A comprehensive set of experiments has been carried out to show the applicability of the proposed scheme over the existing literature. © 2016 IEEE.


Gouverneur B.,Xenics | Verstockt S.,Multimedia Laboratory | Pauwels E.,Centrum Wiskunde and Informatica | Han J.,Centrum Wiskunde and Informatica | And 2 more authors.
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2012

Various visible and infrared cameras have been tested for the early detection of wildfires to protect archeological treasures. This analysis was possible thanks to the EU Firesense project (FP7-244088). Although visible cameras are low cost and give good results during daytime for smoke detection, they fall short under bad visibility conditions. In order to improve the fire detection probability and reduce the false alarms, several infrared bands are tested ranging from the NIR to the LWIR. The SWIR and the LWIR band are helpful to locate the fire through smoke if there is a direct Line Of Sight. The Emphasis is also put on the physical and the electro-optical system modeling for forest fire detection at short and longer ranges. The fusion in three bands (Visible, SWIR, LWIR) is discussed at the pixel level for image enhancement and for fire detection. © 2012 SPIE.


Gaj S.,Multimedia Laboratory | Rana S.,Multimedia Laboratory | Lekharu A.,Multimedia Laboratory | Sur A.,Multimedia Laboratory | Bora P.K.,Indian Institute of Technology Guwahati
2015 5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2015 | Year: 2015

In this paper, a multi-view stereo image watermarking scheme is proposed to resist the RST (rotation, scaling and translation) attack. To make the scheme resilient to RST, the coefficients of Singular Value Decomposition (SVD) from both left and right views have been used for insertion of the watermark bits. 2D-DWT (Discrete wavelet transform) is used as a preprocessing step to get more correlated SVD coefficients of the left and right view such that the visual degradation due to embedding can be reduced. In this work, a blind embedding scheme is proposed by altering the selected SVD coefficients to improve the robustness of the embedding scheme. A comprehensive set of experiments have been performed to justify the robustness of the proposed scheme against RST attack. Moreover, this scheme can be used to detect the view swapping attack using DIBR technique. © 2015 IEEE.


Fukushima R.,Multimedia Laboratory
Kobunshi | Year: 2012

We have commercialized world's first glasses-free digital 3D television at the end of 2010.1 take a look back at three development stages. In the early stage after maternity leave, I enjoyed painting the picture of ideal 3D display in one's own way. In the pre-mass-production stage, I was able to overcome many difficulties with the aid of the cooperation with many coworkers. Finally, I had a delightful commercial stage, which was greatly influenced by the market trends.


Lee S.,Korea Advanced Institute of Science and Technology | De Neve W.,Korea Advanced Institute of Science and Technology | Plataniotis K.N.,Multimedia Laboratory | Ro Y.M.,Korea Advanced Institute of Science and Technology
Pattern Recognition Letters | Year: 2010

Descriptive tags are needed to enable efficient and effective search in vast collections of images. Tag recommendation represents a trade-off between automatic image annotation techniques and manual tagging. In this letter, we formulate image tag recommendation as a maximum a posteriori (MAP) problem, making use of a visual folksonomy. A folksonomy can be seen as a collaboratively created set of metadata for informal social classification. Our experimental results show that the use of a visual folksonomy for image tag recommendation has two significant benefits, compared to a conventional approach using a limited concept vocabulary. First, our tag recommendation technique can make use of an unrestricted and rich concept vocabulary. Second, our approach is able to recommend a higher number of correct tags. © 2009 Elsevier B.V. All rights reserved.


Hollemeersch C.-F.,Multimedia Laboratory | Pieters B.,Multimedia Laboratory | Lambert P.,Multimedia Laboratory | De Walle R.V.,Multimedia Laboratory
Visual Computer | Year: 2012

Texture mapping has been widely used to improve the quality of 3D rendered images. To reduce the storage and bandwidth impact of texture mapping, compression systems are commonly used. To further increase the quality of the rendered images, texture filtering is also often adopted. These two techniques are generally considered to be independent. First, a decompression step is executed to gather texture samples, which is then followed by a separate filtering step. We have investigated a system based on linear transforms that merges both phases together. This allows more efficient decompression and filtering at higher compression ratios. This paper formally presents our approach for any linear transformation, how the commonly used discrete cosine transform can be adapted to this new approach, and how this method can be implemented in real time on current-generation graphics cards using shaders. Through reuse of the existing hardware filtering, fast magnification and minification filtering is achieved. Our implementation provides fully anisotropically filtered samples four to six times faster than an implementation using two separate phases for decompression and filtering. Additionally, our transform-based compression also provides increased and variable compression ratios over standard hardware compression systems at a comparable or better quality level. © Springer-Verlag 2011.

Loading Multimedia Laboratory collaborators
Loading Multimedia Laboratory collaborators