A method for identifying individuals using angled facial data obtained by bright-spots matrix projection

We have already proposed a method for identifying human faces using the three dimensional facial data obtained by setting the fiber grating vision sensor in front of the faces. But in the previous method, there are some problems that these facial data include redundant information because of the bilateral symmetry of the human faces, and in some case, the data behind the nose can't be obtained. In this paper, the authors describe a method for identifying individuals using the angled facial data obtained from the fiber grating vision sensor. We think that we can obtain the more effective data for identifying the faces by setting the fiber grating vision sensor at an angle to the faces. Because we can obtain the effective information from the large region of one side of the faces when we set the sensor like this. In this method, the fiber grating vision sensor which has been developed by the authors, is employed for the three dimensional shape of the faces. Before identifying the facial data, it is necessary to calibrate the position and direction of the facial data. In this method, a set of the directions of normal vectors at data points on the facial surface is obtained, and calibrations are carried out in accordance with the extend of errors in the sets. To identify the human faces, a multi-layered neural network is used in which the inputs are two component values of normal vector on the facial surface. The experiments using the experimental system are performed to demonstrate the efficacy of this method and the experimental results are shown.<>