ConceptRank for search-based image annotation
| Authors | |
|---|---|
| Year of publication | 2018 |
| Type | Article in Periodical |
| Magazine / Source | Multimedia Tools and Applications |
| MU Faculty or unit | |
| Citation | |
| web | https://link.springer.com/article/10.1007/s11042-017-4777-8 |
| Doi | http://dx.doi.org/10.1007/s11042-017-4777-8 |
| Field | Informatics |
| Keywords | Search-based image annotation; Content-based image retrieval; kNN classification; Biased random walk with restarts; Semantic analysis; ConceptRank |
| Description | Multimedia information is becoming an ubiquitous part of our lives, which brings an equally ubiquitous need for efficient multimedia retrieval. One of the possible solutions to this problem is to attach text descriptions to multimedia data objects, thus allowing users to utilize traditional text search mechanisms. Search-based annotation techniques attempt to determine the descriptive keywords by analyzing the descriptions of similar, already annotated multimedia objects, which are detected by content-based retrieval techniques. One of the main challenges of this approach is the extraction of semantically connected keywords from the possibly noisy descriptions of similar objects. In this paper, we address this challenge by proposing the ConceptRank, a new keyword ranking algorithm that exploits semantic relationships between candidate keywords and utilizes the random walk mechanism to compute the probability of individual candidates. The effectiveness of the ConceptRank algorithm is evaluated in context of web image annotation. We present a complex image annotation system that includes the ConceptRank component, and compare it to other state-of-the–art annotation techniques. |
| Related projects: |