Abstract:
The present research is related to human-face recognition using edge-based rasterstereography, which has the potential to be used as identification-based security system. In this respect a modified raster grid is used instead of conventional raster grid. The modification, mainly, consists of equally-spaced circular dots instead of conventional screen composed of stacked squares, which gave acceptable results for green color. This modified raster grid was projected on human face, distortions of which were used to extract curvature information — unique for a face (principal identification and recognition criterion). This information, in coördinate form, was processed by image-processing algorithms. Registration, identification and verification were the three phases
of face-recognition system. In the first step, subject’s face was captured by a digital camera and stored in the system database. In the second phase, the registered face was compared with all the stored faces in the database. In the third phase, verification process executed, which consisted of comparing the identified face with own stored template. Once the facial image passed these three stages, the face was recognized as a particular individual. The algorithm, developed as such was tested on human faces; 380 out of 400 were, correctly, recognized. This algorithm was computationally efficient and effective. The edge-based-rasterstereographic-face-recognition system has been achieved to an extent of efficient 95% for identification and security purposes as
time and cost-saving mechanism.
