Weighting and classification of image features using optimization algorithms

Abstract

In this study, importance ratios of features extracted from images using feature extraction algorithms are examined. A significance coefficient is determined for each feature parameter. The number of features is reduced according to the weight of the importance calculated for each feature. The classification success is examined for each case. Firstly, six feature extraction algorithms are used for this purpose. The classification success of all these feature extraction algorithms has been examined separately. Then, all properties are combined to form a single property matrix. The obtained property matrix is reduced by using principal component analysis and relieff methods. New feature matrices provide increased classification performance. However, it is inefficient to classify a high number of properties in real-Time applications. To overcome this problem, the effect of classifying each parameter in the property matrix is examined and the insignificant properties are discarded. The proposed method is tested using histopathological images. Histopathological images are divided into 4 separate classes. The proposed method reduces the raw feature matrix by 50% with 97.2% classification success. © 2018 IEEE.