Enhanced Feature Selection Method Using Wrapper-based Random Search Strategy and Mutual Information for Remote Sensing Image Classification

Abstract

Remote sensing image classification is one of the useful image processing tasks and finds application in many real-life scenarios. Image feature is important and unavoidable in classification. It is impossible to get a clear classification result without proper features. So after feature extraction, selecting an efficient and relevant feature is inevitable. Thus, our system proposes a new way of selecting features by a wrapper-based method that works using a randomized search strategy. The process is done in an orderly manner. In each step, the features that contribute less to classification are rejected to bring out the most relevant features. Three steps are followed: (1) Randomized selection (2) Warm start and (3) Cool down. The Randomized selection selects relevant features based on the random search method from the full feature set. Among the selected features, the important features are selected, based on the Mutual Information using the Warm start. Some important features, missed out in Randomized selection, are picked up in Cool down. The system finds out 25% of the most relevant features with greater classification accuracy when compared with classification accuracy obtained using 100% features. The proposed system has been checked for its efficiency with the help of remote sensing-based datasets from the UCI repository and it is found to be more efficient than the other existing methods. The results produced with the selected features are of high accuracy and low computational cost.