Image Comparison using HLS Tool |
Author(s): |
| Spoorthi Pakkala , Sahyadri College of Engineering and Management |
Keywords: |
| Histogram, Manhattan Distance |
Abstract |
|
Color is always considered to be an important attribute in content-based retrieval of images. One of the standard ways of extracting a signature from an image is to generate a histogram. During retrieval, the histogram of a query image is compared with the histogram of each of the database images using a standard distance metric. The retrieved result is dependent both on the histogram and the distance metric. The study of the performance of different distance metrics for a number of histograms on a large database of images. We use Manhattan distance, Euclidean distance, Vector Cosine Angle distance and Histogram Intersection distance for performance comparison. The results show that the Manhattan distance performs better than the other distance metrics for all the five types of histograms. The text file generated which contains the pixel values are converted to histogram values and using Manhattan method they are compared. |
Other Details |
|
Paper ID: IJSRDV6I50389 Published in: Volume : 6, Issue : 5 Publication Date: 01/08/2018 Page(s): 676-678 |
Article Preview |
|
|
|
|
