Share This Author
O-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Outdoor Images
- C. Ancuti, C. Ancuti, R. Timofte, C. D. Vleeschouwer
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 13 April 2018
The first outdoor scenes database composed of pairs of real hazy and corresponding haze-free images is introduced, and is used to compare a representative set of state-of-the-art dehazing techniques, using traditional image quality metrics such as PSNR, SSIM and CIEDE2000.
I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images
A new dataset -named I-HAZE- that contains 35 image pairs of hazy and corresponding haze-free (ground-truth) indoor images that allows us to objectively compare the existing image dehazing techniques using traditional image quality metrics such as PSNR and SSIM.
D-HAZY: A dataset to evaluate quantitatively dehazing algorithms
- C. Ancuti, C. Ancuti, C. D. Vleeschouwer
- Computer ScienceIEEE International Conference on Image Processing…
- 19 August 2016
A dataset that contains 1400+ pairs of images with ground truth reference images and hazy images of the same scene, built on the Middelbury and NYU Depth datasets that provide images of various scenes and their corresponding depth maps is introduced.
Circular interpretation of bijective transformations in lossless watermarking for media asset management
Circular interpretation of bijective transformations is proposed to implement a method that fulfills all quality and functionality requirements of lossless watermarking.
Robust video hashing based on radial projections of key frames
- C. D. Roover, C. D. Vleeschouwer, F. Lefèbvre, B. Macq
- Computer ScienceIEEE Transactions on Signal Processing
- 1 October 2005
The proposed RASH feature vector is more robust and provides much stronger discrimination than a conventional histogram-based feature vector, and appears to be a good candidate to build indexing algorithms, copy-detection systems, or content-based authentication mechanisms.
Consistent iterative hard thresholding for signal declipping
- Srdan Kitic, L. Jacques, N. Madhu, Michael Peter Hopwood, A. Spriet, C. D. Vleeschouwer
- Computer ScienceIEEE International Conference on Acoustics…
- 5 March 2013
This work proposes a novel approach for this signal restoration problem based on the framework of Iterative Hard Thresholding, which enforces the consistency of the reconstructed signal with the clipped observations and shows superior performance in comparison to the state-of-the-art declipping algorithms.
Overview on Selective Encryption of Image and Video: Challenges and Perspectives
- Ayoub Massoudi, F. Lefèbvre, C. D. Vleeschouwer, B. Macq, J. Quisquater
- Computer ScienceEURASIP J. Inf. Secur.
This tutorial is intended to give an overview on selective encryption algorithms, which consists of encrypting only a subset of the data while preserving a sufficient level of security.
Human visual system features enabling watermarking
- J. Delaigle, C. D. Vleeschouwer, B. Macq, R. Lagendijk
- Computer ScienceProceedings. IEEE International Conference on…
- 7 November 2002
This paper presents the main features of the human visual system (HVS) to be translated into watermarking technology, and tries to understand, in a synthetic way and from an engineering perspective, the HVS features on which the designer of aWatermarking algorithm can rely, i.e. its sensitivity and masking capabilities.
Single-Scale Fusion: An Effective Approach to Merging Images
A simplified formulation of multi-scale fusion based on the Laplacian pyramid decomposition is introduced that reduces MSF to only a single level process and shows its generality on several well-known fusion-based applications.
Quantized Iterative Hard Thresholding: Bridging 1-bit and High-Resolution Quantized Compressed Sensing
In this work, we show that reconstructing a sparse signal from quantized compressive measurement can be achieved in an unified formalism whatever the (scalar) quantization resolution, i.e., from…