Fuzzy Extended Feature Line Classifier for Image Classification

A new approach called Fuzzy Extended Feature Line (FEFL) is proposed for image classification in this paper, which retain the advantages and ideas of Nearest Feature Line (NFL). The proposed FEFL use NFL to extend the prototype image sample set. Fuzzy K-Nearest Neighbor is applied for adding the new suitable samples to the prototype sample set. Experimental results on ORL face database and finger-knuckle-print database demonstrate the effectiveness of the proposed algorithm.