<![CDATA[It is important to distinguish an individual from a group of other individuals to ensure information security an d integrity. One of human body parts that has distinguishable characterics is the ear. Prior attempts on identification of hum an ear image has been implementing statistical pattern recogni tion which focusing more on classification between sample sets . This research attempts to build a robust ear image recognitio n system using Hyper Sausage Neuron (HSN) that concetrates on cognition process rather than classification. A recognition s oftware has been built and tested to recognize ear images. Ear images presented into the software has its geometrical moment invariants extracted. These moments is then used to build a se ven dimensional feature vector which will construct a network of HSN of each individual it represents. Different ear images f rom the same individual is presented into the software to test i ts accuracy. The experiment result shows that ear recognition using HSN has better accuracy and faster training time than p revious recognition attempts using statistical pattern recogniti on.]]>
