Recent Advances in Scene Image Representation and Classification

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.

arXiv commentThis 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

References in corpus (12)

• Monkeypox virus detection using pre-trained deep learning-based approaches
• Semantic-Aware Scene Recognition
• A Discriminative Representation of Convolutional Features for Indoor Scene Recognition
• Locally-Supervised Deep Hybrid Model for Scene Recognition
• Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition
• Scene Recognition with Prototype-agnostic Scene Layout
• Scene Image Representation by Foreground, Background and Hybrid Features
• Content and Context Features for Scene Image Representation
• HDF: Hybrid Deep Features for Scene Image Representation
• Unsupervised Deep Features for Privacy Image Classification
• Indoor image representation by high-level semantic features
• Tag-based Semantic Features for Scene Image Classification

Cited by in corpus (1)

• Enhanced Multi-level Features for Very High Resolution Remote Sensing Scene Classification