Content Based Image Retrieval Genetic Algorithm for Relevance Feedback
Journal: International Journal of Advanced Computer Research (IJACR) (Vol.2, No. 6)Publication Date: 2012-12-16
Authors : Nikita R. Hatwar Rajendra F. Hatwar;
Page : 381-385
Keywords : Color; Texture; Multispectral Random Field Models; Color Texture Segmentation;
Abstract
Image retrieval using content has become a hot topic in the field of Digital Image Processing and Computer Vision. In this proposed work, we focus on the problem of image retrieval using genetic algorithm for relevance feedback. Texture and Color are the important features in CBIR. Texture and Color is extracted using Multispectral Simultaneous Autoregressive Model (MSAR). The color is represented by ratios of sample color means. The features are extracted by segmenting the image into regions of uniform texture/color using an unsupervised histogram clustering approach that utilizes MSAR and color features. The principle of Genetic Algorithm is based on “survival of the fittest”. After extracting the features Genetic Algorithm (GA) will be applied to retrieve the images from the database. The fittest image will be retrieved.
Other Latest Articles
- Smart Software and Smart Cities: A study on Green Software and Green Technology to develop a smart urbanized world
- Identification of node behavior for Mobile Ad-hoc Network
- Algorithm for Minimizing Network Cost in WDM Network
- Distributed Approach of Intrusion Detection System: Survey
- Half-Wave Dipole Antenna for GSM Applications
Last modified: 2013-01-26 21:02:47