Multispectral Recognition Using Genetic and Evolutionary Feature Extraction

Traditionally, iris recognition systems capture iris images in the 700 to 900nm range. It is within these ranges that researchers have found the most viable iris textures for iris recognition. Recently, there has been an interest for exploration of spectrum ranges that falls outside of these traditional ranges. In this work, we will explore the performance of feature extraction techniques on a wider spectrum, specifically ranges between 400nm to 1550nm. More specifically, we apply the traditional Local Binary Pattern (LBP) technique & a hybrid LBP technique (Genetic and Evolutionary Feature Extraction (GEFE)) in an effort to elicit the most important iris information. We also perform intra-spectral and cross spectrum analysis on the iris images captured in different wavelengths. Results show that GEFE outperforms the LBP technique on all spectrums.