The main objective of this work is to develop a system which can be used to capture the facial images and compare them with the stored facial image data base to identify the person to provide access to highly secured place. The designed system is trained to capture the images in various conditions like dark and light shades, various facial expressions to create a real time database and later when a facial image is captured in any shades and facial expressions the system can easily identify the personality. The designed system "Embedded image capturing and processing system for face recognition" is an authenticating system, which can be interfaced readily with available security systems for enhanced and varied applications. The presently designed system has small dimension, easy portability, high reliability and relatively of less cost comparing to other face recognition systems using PC. A stable test platform has been designed, constructed, tested and the performance of the designed system is found to be encouraging.