Current identification of passive detection has been attention in the modern world due to the system's robustness as an ear recognition framework based on a multiclassifier and attempt to create user patterns via extracted features from ear images, which have unique individual identities. The collected features from the ear intersection points and the angles bounded between curves using different descriptors and classifiers are considered unique information used to generate unique features. The proposed framework commenced with the extraction of eight sets of features (LBP, BSIF, LPQ, RILPQ, POEM, HOG, DSIFT, and Gabor) from 2D ear images. Subsequently, ELM and SVM classifiers were trained on each set of features. Seven combination rules (MR, AR, GWAR, ICWAR, Borda, DS, and AV (GWAR, Borda, DS)) were utilized to acquire a total of 16 classifiers. Also, two optimization rules; genetic algorithm and brute force were proposed for accuracy enhancement. The AWE and the USTB datas.....

532 hits