DEVELOPMENT OF A MODIFIED CLONAL SELECTION ALGORITHM FOR FEATURE LEVEL FUSION OF MULTIBIOMETRIC SYSTEMS
Feature level fusion is the combination of biometric information contained in the extracted features of biometric images. However, feature-balance maintenance and high computational complexity are one of the major problems encountered when fusion is done at feature level. Therefore, in this paper, a Modified Clonal Selection Algorithm (MCSA) which is characterized by feature-balance maintenance capability and low computational complexity was developed for feature level fusion of multibiometric systems.The standard Tournament Selection Method (TSM) was modified by performing tournaments among neighbours rather than by random selection to reduce the between-group selection pressure associated with the standard TSM. Clonal Selection algorithm was formulated by incorporating the Modified Tournament Selection Method (MTSM) into its selection phase. The modified algorithm could be employed for feature level fusion of multibiometric systems.