Institute of Information Theories and Applications FOI ITHEA
Abstract:
The article describes researches of a method of person recognition by face image based on Gabor
wavelets. Scales of Gabor functions are determined at which the maximal percent of recognition for search of
a person in a database and minimal percent of mistakes due to false alarm errors when solving an access
control task is achieved. The carried out researches have shown a possibility of improvement of recognition
system work parameters in the specified two modes when the volume of used data is reduced.