Context-based template matching in iris recognition
Christian Rathgeb, Andreas Uhl · 2010
In general iris recognition algorithms restrict to extracting distinct features out of preprocessed iris images in order to create user-specific iris-codes, neglecting potential improvements in matching procedures. In this work we propose a new way of matching iris-codes. By exploiting local information of extracted iris-codes a context-based matching is performed. The matching procedure is applied to a trivial iris-code generation as well as existing iris recognition systems. Experimental results, according to recognition rates as well as time measurements, emphasize the worthiness of our approach.