Memory Learning Framework for Retrieval of Neural Objects 

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

Comparative Study of Two-way Finite Automata and Turing machine  

Two-way finite Automata are termed as read only Turing machine. Two way finite automata is one of variant of Turing machine, which is blessed with an infinite tape, and could be used by tape head to read or write i...

A Review of a Goal Directed Visual Perception System using Object based Top down Attention 

The tendency of the human being to apply the selective attention mechanism so as to determine about a truly intelligent perception system, which has the cognitive capability of learning and thinking about how to per...

MSNN based techniques for Face and Eye Recognition 

The accurate technique of face recognition effects the performance of a face detection system. An accurate eye localization system is required for better results. There are various techniques for Face and eye det...

A Hybrid Colour Image Enhancement Technique Based on Contrast Stretching and Peak Based Histogram Equalization  

: Medical image enhancement technologies have attracted much attention since advanced medical equipments were put into use in the medical field. Enhanced medical images are desired by a surgeon to assist diagnosi...

The Content Summarization system 

The documents that are published in the internet are represented in the chronological sequence. Any interesting part of this document is called as topic. Topic is the sentence which captures the attention of the re...

Download PDF file
  • EP ID EP162060
  • DOI -
  • Views 113
  • Downloads 0

How To Cite

Sanjeev S. Sannakki, Sanjeev P. Kaulgud (2012). Memory Learning Framework for Retrieval of Neural Objects . International Journal of Advanced Research in Computer Engineering & Technology(IJARCET), 1(6), 100-106. https://europub.co.uk./articles/-A-162060