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

Automated summary

With the rise of deep learning algorithms, scene image representation methods have improved significantly in accuracy for classification. However, the complexity of scene images leads to intra-class dissimilarity and inter-class similarity problems, limiting the overall performance. This paper reviews existing methods and compares their performance qualitatively and quantitatively, while also speculating on future research directions. This survey provides in-depth insights and applications of recent scene image representation methods.