This technology is a fingerprint biometric analysis method to recognize fingerprints across different fingers from the same person.
Identification by fingerprint is routinely used as a tool for authentication security and crime forensics. While this method of biometric verification is often accurate and convenient, it is highly limited in that it is unable to match different fingers from the same person. This renders the technology useless in scenarios where the presented fingerprints are from different fingers than those on record.
This technology demonstrates fingerprint recognition across different fingers from the same person. The technology utilizes deep encoders and machine learning to translate fingerprint images into data that can be analyzed for specific feature correlations. Neural networking is employed to verify that fingerprint feature correlations are not spontaneous and display a genuine pattern. The outcome of the technique is a score of how similar two fingerprints are and the confidence that they belong to the same person.
This technology has been validated with images of human fingerprints.
Patent Pending
