An efficient rotation invariant feature extraction method based on ring projection technique

This study presents an efficient rotation-invariant feature extraction method based on ring projection technique. The main advantage of this method is to reduce the number of sampling frequency of standard ring projection method. The proposed method is compared with the ring projection and local binary patterns according to the computational speed of the feature extraction and classification accuracy. By incrementally rotating first image of each texture class by 30 and 45 degrees enrich the dataset and yield two texture datasets having totally 1332 and 888 samples from the original Brodatz texture image dataset, respectively. Throughout the study Weka machine learning and data mining tool is utilized. As a classifier Naive Bayes, Bagging and J48 decision tree are used due to their simplicity and speed. Classification performance is evaluated via 10 fold cross validation technique. It is observed that, the proposed method outperforms other alternatives in terms of classification accuracy and feature extraction speed.