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.
翻译:随着当今深层次学习算法的崛起,现场图像代表方法在分类方面实现了显著的绩效提升,但表现仍然有限,因为场景图像大多复杂,有较高阶层内部差异和不同阶层之间的相似问题。为了处理这些问题,文献中提出了几种方法,这些方法有其优点和局限性。对以前的工作进行详细研究是必要的,以便了解其质量(例如产出质量、正方/正等)和定量(例如准确性)两方面的绩效。最后,我们审查目前广泛用于图像分类的现有场景图像代表方法。在这方面,我们首先利用文献中为本日期提议的开创性现有方法设计分类方法,利用基于深层次学习(DL)的、基于计算机视觉的和基于搜索引擎的方法。然后,我们比较其质量(例如产出质量、准/正/正等)和定量(例如准确性)的绩效。最后,我们用{关键词增长和时间轴分析,对现场图像代表任务中的突出研究方向进行了推测。}总体而言,这次调查提供了三种不同图像的深度观察和应用。