Abstract | ||
---|---|---|
More images are available nowadays because of the development of techniques to effectively and automatically analyze images. These techniques have become a key challenge in computer vision. In this paper, we focus on the structure of knowledge representation for image analysis from a global perspective, which can also be applied to image classification, retrieval, and object recognition. The structure is divided into two hierarchies, implicit and explicit knowledge representation. Implicit knowledge representation utilizes low-level features to directly categorize an image, whereas explicit knowledge representation depends on the inference process based on corresponding rules in a constructed knowledge base. Popular datasets for image analysis are also grouped and introduced. Contributions in the field and future research directions are reported in the conclusions. |
Year | Venue | DocType |
---|---|---|
2015 | Smart CR | Journal |
Volume | Issue | Citations |
5 | 3 | 5 |
PageRank | References | Authors |
1.77 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhipeng Ye | 1 | 7 | 4.49 |
Peng Liu | 2 | 124 | 33.02 |
Wei Zhao | 3 | 81 | 19.49 |
Xianglong Tang | 4 | 288 | 44.84 |