An Optimal Multi-Level Backward Feature Subset Selection for Object Recognition

Abstract

ABSTRACTFeature subset selection is an active research field in which dimensionality reduction technique is used to select a subset of relevant features. It is a data pre-processing technique used to reduce the number of features in high-dimensional data-sets, crucial in identifying the behaviour and performance of the system. Feature selection finds applications in the areas of image processing, forecasting, document classification, object recognition, anomaly detection, and bioinformatics. The benefits of using feature subset selection include improvements in the data mining algorithm's accuracy, efficiency, and scalability. Feature selection methods are classified into filter and wrapper method, based on the classifier's evaluation strategy. The existing feature subset selection methods are protracted and parameter-dependent, since the user input or threshold value is used to identify the total number of features in the final set. Current feature selection methods result in over estimating feature significance, culminating in the selection of redundant and irrelevant features. To address this issue both theoretically and experimentally, this paper introduced a novel approach to select optimal features for object recognition based on multi-level backward feature subset selection (MLBFSS) algorithm. The proposed method performs better against state-of-the-art methods, verified using benchmark real-world databases. It also outperforms other feature selection methods in terms of classification accuracy and error measures.