A fuzzy transform approach to face recognition using new classifiers

An attempt has been made in this paper to derive the features using the Bandelet and Shearlet Transforms. The transforms are then modified into fuzzy Bandelet and fuzzy shearlet transforms and the same are then applied on the face AT&T database to extract the fuzzy features. These features are then tested with the standard Support Vector Machine classifier to get the recognition rate of about 95%. We have also used the different similarity distance measures to derive three classifiers and the features extracted from Bandelet, Shearlet Fuzzy bandelet and Fuzzy Shearlet Transforms are then classified with these new classifiers and the results thus obtained have shown better improvement over SVM. The new classifiers established for defining the recognition rate are simple and involves less computation.