Image Annotation Based on Color and Texture features
- Resource Type
- Conference
- Authors
- Kong, fanhui
- Source
- 2012 9th International Conference on Fuzzy Systems and Knowledge Discovery Fuzzy Systems and Knowledge Discovery (FSKD), 2012 9th International Conference on. :1225-1228 May, 2012
- Subject
- Components, Circuits, Devices and Systems
Computing and Processing
Communication, Networking and Broadcast Technologies
Image color analysis
Feature extraction
Semantics
Visualization
Training
Vectors
Frequency domain analysis
- Language
This paper presents a method for the establishment of mapping between low-level visual features and high-level semantic features based on Gaussian mixture model (GMM). We combine color features and texture features based on Gabor filter, an image annotation algorithm based on GMM clustering is put forward through the research in image processing. In an image database that contains 1000 images, the experimental results show that the proposed method has better performance.