Optimum Selection of Image Object Attributes for Object-Based Image Analysis and High Classification Accuracy

Object-based image analysis (OBIA) is extensively used for the classification of High-Resolution Satellite Imagery (HRSI). The various attributes of the image segments like spectral, spatial and textural, can be generated for analysis and classification purposes. However, the use of all these attributes may not lead to attaining high classification accuracy. Experiments have shown that, a suitable set of these features need to be identified for faster and accurate classification of imageries. The filter based methods like Chi-Square, Information-gain and ReliefF are extensively used for identification and ranking the best set of parameters. The random tree based Boruta machine learning feature ranking method is also used in identifying the feature ranking along with the above algorithms. Subsequently, a learner is fused with a filter and the resultant receiver operating characteristic (ROC) plot of the model has been used to identify the best accuracy and the minimal set of attributes for identifying an individual feature like roads, trees, grass, buildings and shadow. The best set of parameters for a class is identified by the best ROC plot. The best parameters are identified from Boruta feature analysis. The results indicate that the identified smaller feature set helps in enhancing classification accuracy.