Recent Advances in Scene Image Representation and Classification

TL;DR

This paper reviews recent scene image representation methods, analyzing their advantages, limitations, and performance in classification tasks, and discusses future research directions in the field.

Contribution

It provides a comprehensive taxonomy and comparative analysis of deep learning, computer vision, and search engine-based scene image representation methods.

Findings

Deep learning methods outperform traditional approaches in accuracy.

Trade-offs exist between output quality and computational complexity.

Future research should focus on addressing intra-class dissimilarity and inter-class similarity.

Abstract

With the rise of deep learning algorithms nowadays, scene image representation methods have achieved a significant performance boost 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.