A survey and analysis on automatic image annotation. (July 2018)

• Record Type: Journal Article
• Authors: Cheng, Qimin; Zhang, Qian; Fu, Peng; Tu, Conghuan; Li, Sen
• Is Part Of: Pattern recognition. Volume 79(2018:Jul.)
• Page Start: 242
• Page End: 259
• Publication Date: 2018-07
• Subjects: Automatic image annotation -- Generative model -- Nearest-neighbor model -- Discriminative model -- Tag-completion -- Deep learning; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2018.02.017
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A deep review on state-of-the-art methods in AIA. Discussions on open issues, main challenges, and promising directions. Detailed comparisons of the five types of AIA techniques. Abstract: In recent years, image annotation has attracted extensive attention due to the explosive growth of image data. With the capability of describing images at the semantic level, image annotation has many applications not only in image analysis and understanding but also in some relative disciplines, such as urban management and biomedical engineering. Because of the inherent weaknesses of manual image annotation, Automatic Image Annotation (AIA) has been raised since the late 1990s. In this paper, a deep review of state-of-the-art AIA methods is presented by synthesizing 138 literatures published during the past two decades. We classify AIA methods into five categories: 1) Generative model-based image annotation, 2) Nearest neighbor-based image annotation, 3) Discriminative model-based image annotation, and 4) Tag completion-based image annotation, 5) Deep Learning-based image annotation. Comparisons of the five types of AIA methods are made on the basis of the underlying idea, main contribution, model framework, computational complexity, computation time, and annotation accuracy. We also give an overview of five publicly available image datasets and four standard evaluation metrics commonly used as benchmarks for evaluating AIA methods. Then the performance of some typical or well-behaved models is assessed based on benchmark dataset and standard evaluation metrics. Finally, we share our viewpoints on the open issues and challenges in AIA as well as research trends in the future.