INFORMATION RETRIEVAL FOR IMAGE MINING
Journal Title: International Journal of Research in Computer and Communication Technology - Year 2014, Vol 3, Issue 6
Abstract
Many areas of commerce, government, academia, and hospitals create large collections of digital images. Through digitization of data and developments in technology it is very easy to acquire and store large quantities of data, mainly multimedia data. This data will be suitable to analyse in an efficient and fast manner by the different kinds of agencies of commercial to Military. Currently, tools for mining images are insufficient and require human involvement. Feature selection and extraction is the pre-processing step of Image Mining. Obviously this is a serious step in the whole scenario of Image Mining. Our method to mine from Images – to extract patterns and derive knowledge from large collections of images, deals chiefly with identification and extraction of unique features for a specific domain. Experimental results display that the features used are sufficient to identify the patterns from the Images. An interactive system was established which allows the user to define new features and to resolve unclear regions. This paper presented a new method for image retrieval using high level semantic features. It is based on extraction of low level colour, shape and texture features and their conversion into high level semantic features using fuzzy production rules, derived with the help of an image mining technique. Dempster-Shafer theory of evidence is applied to obtain a list of structures covering information for the image high level semantic features. Johannes Itten theory is helpful for obtaining high level colour features.
Authors and Affiliations
ShashiRekha. B, Dr. K. V. N. Sunitha
Keywords
Related Articles
- EP ID EP27943
- DOI -
- Views 240
- Downloads 0
A New Frame Work and Technique For Earthquake Alert System
As an application, we develop a earthquake reporting structure for use in Japan. In perspective of the different shudders and the tremendous number of Twitter customers all through the country, we can recognize a tre...
Vision Defect Identification System (VDIS) using Knowledge Base and Image Processing Framework
In this research paper, a novel system has been designed which is using two discipline of Computer science area which are Artificial intelligence and image Processing. Fuzzy sets and logic has been chosen from AI and...
A New approach for Cam-Shift Algorithm for Tracking a Moving Object
The main aim of this paper to track a target which plays a key component of video surveillance and monitoring systems. In this paper, we present an new approach to CamShift algorithm and kalman filter for tracking a...
Design and Implementation of Body Movement Recognition System
In this project body movement recognition system based on the Non-vision over the Zigbee Wireless Sensor Network. Now a day's always (day and night time) vision based coma, paralysis patient’s posture information can...
Optimum Image Filtering Algorithm Over The Unit Sphere
A statistical shape model, which includes a network of deformable curves on the unit sphere as reference framework for seeking geometric features such as high curvature regions and labels such features via a deforma...