- Title
- Colour image annotation using hybrid intelligent techniques for image retrieval
- Creator
- Kulkarni, Siddhivinayak; Kulkarni, Pradnya
- Date
- 2012
- Type
- Text; Conference proceedings
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/58046
- Identifier
- vital:4918
- Identifier
-
https://doi.org/10.1109/HIS.2012.6421319
- Abstract
- This paper presents a novel technique for colour image annotation based on neural networks and fuzzy logic. Neural network is proposed for classifying the images based on their contents and fuzzy logic is proposed for interpreting the content of an image in terms of natural language. One of the main aspects of this research is to avoid re-training of the neural networks by training the content of the image. Neural network is not trained on database of images; therefore image can be added or deleted from image database without affecting the training. The proposed hybrid technique is tested on real world colour image dataset and promising results are obtained. © 2012 IEEE.
- Publisher
- Pune, India IEEE
- Rights
- Copyright 2012 IEEE
- Rights
- Open Access
- Rights
- This metadata is freely available under a CCO license
- Subject
- Colour image; Hybrid techniques; Image annotation; Image database; Intelligent techniques; Natural languages; Novel techniques; Fuzzy logic; Image analysis; Intelligent systems; Neural networks; Image retrieval
- Full Text
- Hits: 2258
- Visitors: 2921
- Downloads: 376
Thumbnail | File | Description | Size | Format | |||
---|---|---|---|---|---|---|---|
View Details Download | SOURCE1 | Accepted Version | 185 KB | Adobe Acrobat PDF | View Details Download | ||
View Details Download | SOURCE2 | Published Version | 211 KB | Adobe Acrobat PDF | View Details Download |