Electronics and Telecommunications Research Institute

Inha-Industry Partnership Institute

Sung Bum Pan

Kyo Il Chung

Dae Sung Moon

Min Soo Kim

Kichul Kim

Yong Jin Lee

Kyung Hee Lee

Chee Hang Park

Youn-Hee Gil

Yongwha Chung

Hak Il Kim

Youngwha Chung

Do Sung Ahn

Ji Hyun Moon

A face feature extraction apparatus and method are provided. The face feature extraction apparatus for used in a two-dimensional (2D) face identification system includes: a local base vector generator generating a plurality of local base vectors to extract features of portions of a face from input 2D face image data of users; a local base vector selector selecting a predetermined number of local base vectors suitable for the face identification from the plurality of local base vectors generated by the local base vector generator; and a local base vector overlapper overlapping the local base vectors selected by the local base vector selector and generating a smaller number of overlapped local base vectors than the selected local base vectors. Thus, 2D face identification system having high face identification rate can be provided.

Face feature extraction apparatus and method

A method and apparatus for classifying fingerprint image quality and a fingerprint image recognition system are provided. The method includes dividing a fingerprint image into a plurality of blocks, calculating and vectorizing quality classification parameters with respect to the respective blocks, obtaining quality classification values for the respective blocks by inputting the vectorized quality classification parameters into a trained quality classifier, and selecting a representative value of the quality classification values and determining the representative value as the quality of the fingerprint image. Since the quality of the fingerprint image can be accurately judged, reliability of the fingerprint image recognition system is increased.

Method and apparatus for classifying fingerprint image quality, and fingerprint image recognition system using the same

Provided are a method and apparatus for identifying a fingerprint. The method uses minutiae points of the fingerprint and includes (a) enrolling a fingerprint of a first user in a first database by extracting n minutiae points from a fingerprint image of the first user; selecting one of the n minutiae points as a reference point; rotating the other minutiae points by a predetermined angle with respect to the reference point; generating a first user table containing information regarding the first user's fingerprint based on geometrical changes of the other minutiae points which are obtained by the rotation; and storing the first user table in the first database; and (b) identifying a fingerprint of a second user by extracting m minutiae points from a fingerprint image of the second user; selecting one of the m minutiae points as a reference point; generating a second user table containing information regarding the second user's fingerprint based on geometric changes of the other minutiae points obtained by rotating the other minutiae points by an angle about the reference point; comparing the second user table with the first user table, and selecting a similar candidate list of user tables (m and n are integers). Accordingly, it is possible to enroll a large amount of information regarding fingerprints in a database using quantization and geometric hashing while using a limited storage memory of a central database. Further, it is possible to accurately identify and detect a user's fingerprint in real time using geometric hashing and parallel processing.

Method and apparatus for identifying a fingerprint

In an apparatus for authenticating a user by employing feature points of a fingerprint image of the user, a fingerprint image input circuit scans a fingerprint of a user to be registered to provide a first fingerprint image and a fingerprint of a user to be authenticated to provide a second fingerprint image. A host provides registered feature points data corresponding to the first fingerprint image and target feature points data corresponding to the second fingerprint image. A security token circuit estimates a position difference and a direction difference between pairs of a registered feature point and a target feature point and corrects the two feature points based on the position difference and the direction difference to provide authentication result data.

Apparatus and method for authenticating a user by employing feature points of a fingerprint image of the user

Growing community of inventors

Daejeon, South Korea

Sung Bum Pan