Content-based image retrievals based on generalised gamma distribution and relevance feedback mechanism
by T.V. Madhusudhanarao; S. Pallam Setty; Y. Srinivas
International Journal of Computational Vision and Robotics (IJCVR), Vol. 5, No. 3, 2015

Abstract: The modern technological developments have made significant strides in the usage of internet and made it possible to store and access voluminous data across the globe. These developments have brought certain disadvantages with regard to retrieval of images of interest and also while storing the images. These retrievals play a crucial role in the areas like content-based image retrievals (CBIR). CBIR has wide advantages in areas like security, medical domain where based on the features, the images are to be retrieved. It is therefore necessary to retrieve the interest of images based on certain keyword or features which helps towards faster retrieval of the images. Since the number of images available in the internet is increasing, it is therefore necessary to extract the images based on relevance and query. This paper mainly focuses on the retrieval of the images based on generalised gamma distribution (GGD). The technique employed in this paper is based on the input query and extracting the vital information based on the relevancy. The performance of the developed model is tested using metrics like precision and recall. The methodologies also compared with the available existing methods based on GMM and skew GMM using evaluation metrics. The proposed model exhibited significant performance.

Online publication date: Fri, 21-Aug-2015

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Vision and Robotics (IJCVR):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com