Abderrahim Mesbah
Sidi Mohamed Ben Abdellah University
24 Papers
100 Citations
Abderrahim Mesbah is an academic researcher from Sidi Mohamed Ben Abdellah University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 7, co-authored 19 publications. Previous affiliations of Abderrahim Mesbah include SIDI & Mohammed V University.
Chat about Author
Papers
Lip reading with Hahn Convolutional Neural Networks
Abderrahim Mesbah,Aissam Berrahou,Hicham Hammouchi,Hicham Hammouchi,Hassan Berbia,Hassan Qjidaa,Mohamed Daoudi +6 more
TL;DR: A novel architecture based on Hahn moments as first layer in the Convolutional Neural Network (CNN) architecture is proposed, and it is shown that HCNN helps in reducing the dimensionality of video images, in gaining training time.
53
Fast and efficient computation of three-dimensional Hahn moments
TL;DR: The proposed algorithm enormously reduces the computational complexity of a 3-D Hahn moment and its inverse moment transform and can be also implemented easily for high order of moments.
23
3D radial invariant of dual Hahn moments
TL;DR: New sets of 2D and 3D rotation invariants based on orthogonal radial dual Hahn moments, which are Orthogonal on a non-uniform lattice are proposed and performed better than the radial Tchebichef and Krawtchouk moments, with and without noise.
20
Radial Charlier moment invariants for 2D object/image recognition
M. El Mallahi,Abderrahim Mesbah,Hicham Karmouni,A. El Affar,Ahmed Tahiri,Hassan Qjidaa +5 more
- 01 Sep 2016
TL;DR: Experimental results show the efficiency and the robustness to reconstruction error (MSE), peak signal to noise ratio (PSNR) of the proposed method to construct a set of rotation invariants extracted from radial Charlier moments (RCMI).
16
Deformable 3D Shape Classification Using 3D Racah Moments and Deep Neural Networks
TL;DR: A new model for 3D shape classification based on 3D image Racah moments and deep neural networks to enhance the classification accuracy and reduce the computational complexity of 3D object recognition is proposed.
15