Name Plate Identification for Realizing Key-less Office

Abstract

For the control of incoming and outgoing persons through the gates of security rooms in offices, a method of identifying individuals by using an image of the name plate which is usually clipped on each breast of workers is proposed. Before the identification, the calibration of the image data is carried out against the three dimensional directions of name plates at the time the images were obtained. This process is carried out by transferring the two dimensional image to the image which is estimated that it would be obtained in the case of setting the camera opposite to the name plate accurately. The identification of the characters on the name plates is accomplished by using a neural network. In this paper, the authors describe the results of the experiments which were performed to demonstrate the effectiveness of the proposed method.