Hadoop based Image Retrieval using CDLEP and Gabor Features |
Author(s): |
| P Rohini , ICFAI Foundation for Higher Education; L Koteswara Rao, ICFAI Foundation for Higher Education |
Keywords: |
| Color, Gabor Filters, LBP, DLEP, Image Retrieval, Hadoop, Mapreduce, Precision, Recall |
Abstract |
|
The Directional Extrema Patterns are used to encode the relationship between the centre pixel and its neighbors by computing the edge information in four directions. The proposed work focuses on developing a feature vector for CBIR system with the combination of color DLEP and Gabor features to make the final feature vector. Local Binary Pattern (LBP) operator has become very useful in image retrieval, where a centre pixel is compared with surrounding pixels to obtain a feature vector. However, the directions are not obtained in this method. In this paper, we propose a new method to improve the performance of the retrieval system with the help of Hadoop framework. The main objective is distribution of image data over a large number of nodes over Hadoop using Map Reduce Technique. Hadoop defines a framework which allows processing on distributed large sets across clusters of computer. |
Other Details |
|
Paper ID: IJSRDV5I30796 Published in: Volume : 5, Issue : 3 Publication Date: 01/06/2017 Page(s): 800-804 |
Article Preview |
|
|
|
|
