Rate My Professor Mustapha Kardouchi

Mustapha Kardouchi is a professeur titulaire in the Département d'informatique at the Université de Moncton, part of the Faculté des sciences on the Campus de Moncton. He earned his PhD in Medical Informatics from the University of Burgundy in Dijon, France, in 1998. His professional career at the Université de Moncton includes supervision of master's theses, service on academic juries and committees, and contributions to departmental promotions and permanences. Kardouchi has been affiliated with various campuses of the university, including Shippagan in earlier research works. His specializations encompass medical imaging, digital angiography and ultrasound, deformable models, optical flow, and image processing, as listed on the departmental faculty page.

Kardouchi's research interests span computer vision techniques for specular reflections removal, colposcopic image analysis, image retrieval and segmentation; sign language recognition focusing on Arabic and Moroccan sign languages using convolutional and recursive neural networks; face recognition systems based on random forests, histograms of oriented gradients, Gabor features, and hidden Markov models; neural networks including encoder-decoder models; birdsong recognition with autoregressive time-delay neural networks; fuzzy logic and shape contexts for indexing; and wireless sensor networks. Key publications include 'Automatic detection and inpainting of specular reflections for colposcopic images' (Central European Journal of Computer Science, 2011, cited by 89); 'Arab sign language recognition with convolutional neural networks' (International Conference on Computer Science and Renewable Energies, 2019, cited by 82); 'Fast and efficient face recognition system using random forest and histograms of oriented gradients' (BIOSIG Conference, 2012, cited by 33); 'Automatic birdsong recognition based on autoregressive time-delay neural networks' (ICSC Congress, 2005, cited by 33); 'Isolated video-based Arabic sign language recognition using convolutional and recursive neural networks' (Arabian Journal for Science and Engineering, 2022, cited by 31); 'Improving bag of visual words image retrieval: A fuzzy weighting scheme for efficient indexation' (Signal-Image Technology and Internet-Based Systems Conference, 2009, cited by 31); 'Handwritten tifinagh characters recognition using deep convolutional neural networks' (Sensing and Imaging, 2019, cited by 28); and 'Estimation of large-amplitude motion and disparity fields: Application to intermediate view reconstruction' (Visual Communications and Image Processing, 2001, cited by 14). He has served as guest editor for special issues on machine learning and data analysis for image processing and co-chairs sessions at international conferences on imaging and pattern analysis.