Human iris pattern recognition using phase components of image

The increase in security concerns on issues such as identity, theft indicates the needs of a new reliable security system. Iris recognition is perhaps the most accurate means of personnel identification due to the uniqueness of the patterns contained in each iris. This paper presents new image processing algorithm which specifically focuses on the characteristics of the phase components obtained from two-dimensional Fourier Transformation of image. The Phase Only Correlation (POC) and Band Limited Phase Only Correlation (BLPOC) are the most fundamental transformations, the features of which include superior discrimination capability over the ordinary recognition system.