Fingerprint is a unique feature to an individual. It stays with a person throughout his or her life.
This makes the fingerprint the most reliable kind of personal identification because it cannot be forgotten, misplaced, or stolen. Fingerprint authorization is potentially the most affordable and convenient method of verifying a person's identity.
The lines that create a fingerprint pattern are called ridges and the spaces between the ridges are called valleys. It is through the pattern of these ridges and valleys that a unique fingerprint is matched for verification and authorization.
Our algorithm is based on the minutiae, such as ending, bifurcation, and singular points in the fingerprint images, which have been known to be effective clues for fingerprint verification. Moreover, global ridge information is also utilized to overcome the shortcomings of local minutiae features, resulting in the outstanding verification performance. The algorithm is divided into two major processing components, feature extractor and matcher.
Input fingerprint images captured from the sensors are noisy, in poor contrast, containing much flaw and smudge. Based on intensive analysis of the image characteristics, powerful image enhancement technique is developed, yielding high quality ridge image. Moreover, a lot of erroneous features are efficiently removed by noisy area reduction technique.
Generally, there are tradeoffs between matching speed and discriminating performance in conventional technologies. Our matching engine provides both fast matching speed and outstanding matching performance on noisy features, so that our algorithm is easily applied to the embedded systems, controlled by low-cost slow processors. And it also has the merit in searching large database.
Our algorithm is platform independent, enabled by low memory constraint, fast verification speed, and simple standard operations. This functionality enables the customers to integrate various platforms, such as PC and various controller or DSP based embedded modules.