Face^3 a 2D+3D Robust Face Recognition System

Abstract

We present Face 3 , a system for the automatic recognition of people using 2D and 3D images. The system implements several innovative algorithms. A full 3D face detector allows the detection of faces regardless their pose and orientation in the scene. A face restoration module allows the recognition even in presence of occlusions. The recognition is performed using a fusion of 2D and 3D data. Finally, in order to relax the hardware constraints, a simplification algorithm is used to reduce the data complexity of the 3D face models.

Multi-scale edge detection on range and intensity images

“…However, techniques for feature extraction in range images are not as readily available as in intensity images [3,18], and moreover approaches for feature extraction in intensity or range images can only be applied to the specific image type for which they were designed; none of the approaches could be readily applied to both intensity and range images without performing an image pre-processing. As much research has been undertaken in trying to integrate 2D and 3D images, specifically in application areas such as medical imaging [13] and face recognition [12,27], we believe that a single approach that can be used on both image types (i.e. both intensity and range) would greatly aid the process of an image fusion.…”

An Adaptive Technique for Accurate Feature Extraction from Regular and Irregular Image Data

“…Typically approaches for feature extraction in intensity or range images can only be applied principally to that specific image type; none of the typical approaches can be readily applied to both image types without image preprocessing. As much research has been undertaken in trying to integrate 2D and 3D images [2], specifically in application areas such as medical imaging [6] and face recognition [5,21], we believe that a single approach that can be used on both image types would greatly aid the process of image fusion.…”