Neural Network approach for image retrieval based on preference elicitation
Journal Title: International Journal on Computer Science and Engineering - Year 2010, Vol 2, Issue 4
Abstract
Multimedia technologies have been developing rapidly over the last few years and have yielded a large umber of databases containing graphical documents. Tools for content-based search of graphical objects have been the subject of intensive research, but their performance is still unsatisfactory for many applications, opening up afield for further research and echnology development. Up till now, all popular Internet search engines have been only text-based, including those that search for images. In this paper We propose an image retrieval system based on neural networks. The advantage of using the neural network is that the amount of semantic gap can be reduced when compared to other echniques which may be based on clustering. The ethodology proposed below is esigned for a specific class of objects, hich can be broken down into subobjects in such a way that the main object can be classified by shape, color distribution and texture of the sub objects and the spatial spatial relations between the b-objects in a 2- dimensional image. We also assume that translation, scaling and 2D rotation do not change the class of the object, but we d not consider 3Dtransformation.Therefore, photos of the same 3D object from different positions for xample are considered to be objects belonging to different class.
Authors and Affiliations
B. Veera Jyothi , Dr. Uma Shanker
Keywords
Related Articles
- EP ID EP155293
- DOI -
- Views 107
- Downloads 0
Efficiency of K-Means Clustering Algorithm in Mining Outliers from Large Data Sets
This paper presents the performance of k-means clustering algorithm, depending upon various mean values input methods. Clustering plays a vital role in data mining. Its main job is to group the similar data together base...
Speech Volume Monitor for Hearing Impaired
Hearing impaired can be classified into people who were affected by birth and those who developed the problem at a later stage. The second category knows how to speak but cannot hear them. They encounter embarrassment by...
A Novel Biometric system for Person Recognition Using Palm vein Images
The palm vein is one of the most reliable physiological characteristics that can be used to distinguish between individuals. In recent years, it receives more attention from the researchers. In this paper, we present a n...
An Algorithm for Finding Frequent Itemset based on Lattice Approach for Lower Cardinality Dense and Sparse Dataset
Whenever mining association rules work for large data sets frequently itemset always play an important role and enhance the performance. Apriori algorithm is widely used for mining association rule which uses frequent it...
E-Commerce Security using PKI approach
As a most popular business model, ECommerce provides a more convenient business mode and lower transaction cost. Currently Ecommerce security is still an obstacle in evelopment of e-commerce. It is the need of the hour...