M
Mohamed-Chaker Larabi
Researcher at University of Poitiers
Publications - 185
Citations - 2305
Mohamed-Chaker Larabi is an academic researcher from University of Poitiers. The author has contributed to research in topics: Human visual system model & Image quality. The author has an hindex of 16, co-authored 175 publications receiving 2059 citations. Previous affiliations of Mohamed-Chaker Larabi include Centre national de la recherche scientifique.
Papers
More filters
Proceedings ArticleDOI
Using combination of color, texture, and shape features for image retrieval in melanomas databases
TL;DR: This paper deals with Computer Aided Diagnosis for skin cancers (melanomas) with some rules based on some rules called the ABCD mnemonics, which take into account color distribution, lesion's diameter, etc.
Proceedings ArticleDOI
Using monocular depth cues for modeling stereoscopic 3D saliency
TL;DR: In this article, a stereoscopic 3D saliency model relying on 2D salience features jointly with depth obtained from monocular cues was proposed, and the validation of the model using state-of-the-art procedures including Kullback-Leibler divergence (KLD), area under the curve (AUC), and correlation coefficient (CC) in comparison with attention maps showed very good performance.
Proceedings ArticleDOI
HVS-based quantization steps for validation of digital cinema extended bitrates
Mohamed-Chaker Larabi,Pascal Pellegrin,G. Anciaux,F.-O. Devaux,O. Tulet,Benoît Macq,C. Fernandez +6 more
TL;DR: The work presented in this paper is intended to define quantization steps ensuring the visually lossless compression, and shows that it is necessary to increase the bitrate limit for cinema material in order to achieve the visually Lossless compression.
Journal ArticleDOI
A reduced reference video quality assessment of H.264 and mpeg2 codec based on sharpness metric
TL;DR: In this paper, a new perceptually significant video quality metric for the H.264/Motion Picture Expert Group (MPEG)-4 Advanced Video Coding (AVC) and MPEG2 standard is proposed.