Antonio Rama

Learn More
This paper presents a new technique for face recognition that can cope with partial occlussion or strong variations in facial expression. The method tries to solve the face recognition problem from a near-holistic perspective. The main idea is to " eliminate " some features which may cause a reduction of the recognition accuracy under occlusion or(More)
Face recognition based on 3D techniques is a promising approach since it takes advantage of the additional information provided by depth which makes the whole approach more robust against illumination and pose variations. However, these 3D approaches require the cooperation of the person to acquire accurate 3D data; thus, they are not appropriated for some(More)
The paper presents a novel face detection and tracking algorithm which could be part of human-machine interaction in applications such as intelligent cash machine. The facial feature extraction algorithm is based on discrete approximation of Gabor Transform, called Discrete Gabor Jets (DGJ), evaluated in edge points. DGJ is computed using integral image for(More)
This paper presents a novel face recognition approach which uses only partial information in the recognition stage. The algorithm is based on an extension of the classical PCA and is called Partial PCA (P2CA). The P 2 CA is a combined 2D-3D scheme which requires 3D face data in the training process but can process 2D pictures in the recognition stage. The(More)
– Partial Principal Component Analysis has demonstrated to be a robust face recognition approach a also for big pose variations. The main idea behing P 2 CA is to use 3D (2.5D) data during the training stage but then it can use a single 2D image in the recognition stage, in order to be useful for pose variations. Nevertheles this approach present two major(More)
In our previous work we presented a new 2D-3D mixed face recognition scheme called Partial Principal Component Analysis (P 2 CA) [1]. The main contribution of P 2 CA is that it uses 3D data in the training stage but it accepts either 2D or 3D information in the recognition stage. We think that 2D-3D mixed approaches are the next step in face recognition(More)