Eigenface recognition derives it's name from the German prefix "eigen", meaning "own" or "individual" (Ponti, 1999). The eigenface recognition approach was developed by Turk and Pentland (1991), both colleagues from MIT, in 1987. The eigenface method of facial recognition is considered the first working facial recognition technology (Velasco, 1998).

The eigenface recognition system begins by collecting a large number of facial images in a database. The system then creates a set of eigenfaces by combining all of the facial images in the database and comparing commonalities and differences between groups of individual facial images (Velasco, 1998). The eigenfaces developed by the system appear as two-dimensional sets of light and dark areas arranged in a particular pattern. When a face is presented to the eigenface system for identification, the location of the eyes are found first. The eye location provides a reference point so the head can be located and scaled to a standard size. Next, the system concentrates on the face only, leaving out clothing and hair, and removing brightness and contrast variations caused by the cameras settings (Lau Technologies, 1999). Then the program compares the live face's eigenface characteristics with those in the database and determines a "degree of fit" score, between -1.0 and +1.0,  for the target face. If the target face produces a high enough degree of fit score when compared to a face stored in the database, it is recognized and accepted by the system (Ruggles, 1998). Practically any individual can be identified using a database of 100 to 150 eigenfaces (Velasco, 1998).

A variation of the eigenface approach, called eigenfeatures, is also being developed. The eigenfeature approach combines facial metrics, which involves measuring the distance between specific facial features, such as the eyes, nose, and mouth, with the eigenface approach. The eigenfeatures system measures the distance between these points on a live face and compares them to the sets of eigenfeatures stored in the database to determine whether the face is a match (Randall, 1999).

The primary advantage of the eigenface method is the system's speed and efficiency. The eigenface approach reduces the amount of data needed to identify an individual to 1/1000th of a full sized image (Lau Technologies, 1999).

The eigenface recognition system was the first working facial recognition system. The eigenface method provides accurate recognition rates, but has difficulty when presented with face deformities, such as scarring. The eigenface method also has problems identifying faces in different light levels and pose positions. The face must be presented to the system as a frontal view in order for the system to work.

When the eigenface method is combined with the eigenfeatures method, the system becomes much more versatile. Greater accuracy can be achieved because of the eigenfeatures method's ability to identify faces with variations such as beards and glasses (Randall, 1999).

West Virginia motor vehicle branches are presently using eigenface recognition technology when renewing driver's licenses. The systems were installed to combat fraudulent driver's licenses from being printed and used for criminal purposes, such as false identification (ScanThis, 1997).