Recent advances in scene image representation and classification

With the rise of deep learning algorithms nowadays, scene image representation methods have achieved a significant performance boost in classification. However, is still limited because images are mostly complex having higher intra-class dissimilarity and inter-class similarity problems. To deal with such problems, there been several proposed literature their advantages limitations. A detailed study previous works necessary to understand disadvantages classification In this paper, we review existing that being widely used for For this, we, first, devise taxonomy using seminal date {using (DL)-based, computer vision (CV)-based, search engine (SE)-based methods}. Next, compare both qualitatively (e.g., quality outputs, pros/cons, etc.) quantitatively accuracy). Last, speculate on prominent research directions tasks {keyword growth timeline analysis.} Overall, survey provides in-depth insights applications recent under three different methods.