The field of Pattern Recognition (PR) explores ways to interpret and categorize patterns that emerge in our world by machine. In order to achieve this task there is a strong need for theoretical development as well as practical methods. Research in Pattern Recognition Lab (PRL) focus on development of new and enhanced algorithms to analyze patterns collected from sensors. A pattern recognition problem is typically solved using three fundamental actions after the information reaches the sensor: preprocessing, feature extraction and classification. The inputs to the PR systems explored here are typically extracted from a sensor to a digital form, for example a digital image.
Examples of Areas in PRL
aims at identifying person based on our fingerprints. Varying fingerprint quality, age of persons and different sensors constitute a major problem in correct matching. The focus is to investigate and design fully automated fingerprint matching algorithms addressing these issues, in particular handling inter sensor interoperability without manual tuning of parameters.
explores ways to find and match patterns found on the human face. Aims at addressing issues such as varying illumination and investigates new feature extraction methods as well as classifiers for faces in images. Further, evaluates ways to utilize features and classifiers in the design of algorithms towards applications related to face processing.
employs pattern extraction and matching for human identification from irides by machine. The precise iris borders marking, low and varying illumination issues, more accurate matching algorithms and potential use at a distance are desired goals for future capabilities in iris recognition technology.