English

Recent Advances in Scene Image Representation and Classification

Computer Vision and Pattern Recognition 2023-06-13 v2

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.

Keywords

Cite

@article{arxiv.2206.07326,
  title  = {Recent Advances in Scene Image Representation and Classification},
  author = {Chiranjibi Sitaula and Tej Bahadur Shahi and Faezeh Marzbanrad and Jagannath Aryal},
  journal= {arXiv preprint arXiv:2206.07326},
  year   = {2023}
}

Comments

This paper is under review in Multimedia Tools and Applications (Springer) journal. This article may be deleted or updated based on the policies of the journal

R2 v1 2026-06-24T11:51:53.823Z