Thème :
3D Face recognition using Handcrafted and Machine Learning based methods
Présentation :
3D face recognition has become a very active area of research in recent years. Various methods using 2D image analysis have been presented to tackle these problems. 2D image-based methods are inherently limited by variability in imaging factors such as illumination and pose. The recent development of 3D acquisition sensors has made 3D data more and more available. Such data is relatively invariant to illumination and pose, bu it is still sensitive to expression variation. Our research aims to propose efficient methods for 3D face recognition/verification under different variations such as expression, illumination, pose and image quality.
Thème :
Alzheimer’s disease detection
Présentation :
Alzheimer’s disease is a major public health problem. This eurodegenerative pathology mainly affects people over 65 years old. Therefore, early detection of AD is become an active research area in recent years. Medical images are more and more available in various forms such as magnetic resonance imaging (MRI), ultrasound, X-ray scanner, radiology. Based on these images, we aim to propose an efficient systems to early detect the Alzheimer's desease using handcrafted and/or deep features-based methods.
Thème :
Facial expression recognition using Handcrafted and Machine Learning-based methods
Présentation :
The problem of person-independent facial expression recognition has been studied in many computer vision researches due to its various applications such as human computer interaction, medicine and psychological investigations.
The recognition of the movements of the eyes, mouth, and facial muscles has attracted a great amount of researchers in the past decade. Our research focuses on the implementation of robust facial expression recognition methods againt different variations such as illumination, pose image quality and indesired parts.