Memory Learning Framework for Retrieval of Neural Objects
Journal Title: International Journal of Advanced Research in Computer Engineering & Technology(IJARCET) - Year 2012, Vol 1, Issue 6
Abstract
Most current content-based image retrieval systems are still incapable of providing users with their desired results. The major difficulty lies in the gap between low-level image features and high-level image semantics. To address the problem, this study reports a framework for effective image retrieval by employing a novel idea of memory learning. It forms a knowledge memory model to store the semantic information by simply accumulating user-provided interactions. A learning strategy is then applied to predict the semantic relationships among images according to the memorized knowledge. Image queries are finally performed based on a seamless combination of low-level features and learned semantics. One important advantage of our framework is its ability to efficiently annotate images and also propagate the keyword annotation from the labeled images to unlabeled images. The presented algorithm has been integrated into a practical image retrieval system. Experiments on a collection of large number of images demonstrate the effectiveness of the proposed framework.
Authors and Affiliations
Sanjeev S. Sannakki , Sanjeev P. Kaulgud
Keywords
Related Articles
- EP ID EP162060
- DOI -
- Views 119
- Downloads 0
Scaling of Dimensions & Gate Capacitances of MOSFET
The scaling of complementary metal oxide semiconductor (CMOS) transistors has led to the silicon dioxide layer used as a gate dielectric becoming so thin (1.4 nm) that its leakage current is too large. It is necess...
ESW-FI: An Improved Analysis of Frequent Itemsets Mining
Frequent itemsets mining play an essential role in many datamining tasks. The frequent itemset mining over data streams is to find an approximate set of frequent itemsets in transaction with respect to a given supp...
Routing Issues for Trust Based Framework in Mobile Ad Hoc Networks
The execution and survival of ad hoc networks depends on cooperative and trusting nature of the distributed nodes. There is a common assumption in the routing protocols that all nodes are trustworthy and cooperative....
VisualRank for Image Retrieval from Large-Scale Image Database
VisualRank provide ranking among images to be retrieved by measuring common visual features of the images. The similarity between images is measured by measuring similarity within extracted features like Texture, C...
A BRIEF SURVEY ON THE CONCEPTS OF AGENT AND ARTIFICIAL IMMUNE SYSTEMS
Agents are probably the fastest growing area Information Technology. As agents has ability to migrate to any system, perform the tasks and return the results. The field of software agents is a broad and rapidly dev...