Image region label refinement using spatial position relation graph
| Autor: | Zhe Wang, Mu Yakun, Wang Zhenkun, Jing Zhang |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Information Systems and Management
Computer science business.industry Relation graph Pattern recognition 02 engineering and technology Management Information Systems Image (mathematics) Spatial relation Annotation Automatic image annotation Artificial Intelligence Position (vector) 020204 information systems 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Software Semantic gap |
| Zdroj: | Knowledge-Based Systems. 166:82-91 |
| ISSN: | 0950-7051 |
| DOI: | 10.1016/j.knosys.2018.12.010 |
| Popis: | With the exponential growth of massive image data, automatic image annotation is becoming more important in image management and retrieval. Traditional image region annotation methods, through machine learning and low-level visual features, typically yield incorrect annotation results owing to the influence of the Semantic Gap. We herein propose a novel label refinement method for improving the image region annotation results. A spatial position relation graph with co-occurrence relations and spatial position relations among labels is proposed to analyze the latent semantic correlations among image region labels. Moreover, an incremental iterative random-walking algorithm is proposed to reconstruct the region relation graph for detecting non-dependable regions whose labels do not fit the semantic context of an image. Subsequently, a graph matching algorithm with semantic correlation and spatial relation analysis is proposed for non-dependable region label completion. Experiments on Corel5K demonstrate that our proposed spatial-position-relation-graph- based label refinement method can achieve good performance for image region label refinement. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect