Crysdian, Cahyo ORCID: https://orcid.org/0000-0002-7488-6217
(2023)
*The evaluation of entropy-based algorithm towards the production of closed-loop edge.*
Joiv: International Journal on Informatics Visualization, 7 (4).
pp. 2481-2488.
ISSN 25499904

Text
18705.pdf - Published Version Available under License Creative Commons Attribution Share Alike. Download (4MB) |

## Abstract

This research concerns with the common problem of edge detection that suffers from producing a disjointed and incomplete edge leading to misdetection of visual object. The entropy-based algorithm has a potential to solve this problem by classifying the pixel belonging to which objects in an image. Hence, the paper aims to evaluate the performance of entropy-based algorithm to produce the closed-loop edge representing the formation of object boundary. The research utilizes the concept of entropy to sense the uncertainty of pixel membership to the existing objects in order to classify pixel as the edge or object. Six entropy-based algorithms are evaluated, i.e. the optimum entropy based on Shannon formula, the optimum of relative-entropy based on Kullback-Leibler divergence, the maximum of optimum entropy neighbour, the minimum of optimum relative-entropy neighbour, the thinning of optimum entropy neighbour, and the thinning of optimum relative-entropy neighbour. The experiment is held to compare the developed algorithms against Canny as a benchmark by employing five performance parameters, i.e., the average number of detected objects, the average number of detected edge pixels, the average size of detected objects, the ratio of the number of edge pixel per object, and the average of ten biggest size. The experiment shows that the entropy-based algorithms significantly improve the production of closed-loop edge, and the optimum of relative-entropy neighbour based on Kullback-Leibler divergence becomes the most desired approach among others due to the production of bigger closed-loop edge in the average. This finding suggests that the entropy-based algorithm becomes the best choice to support edge-based segmentation. The effectiveness of entropy in segmentation task is addressed for further research.

### Downloads

Downloads per month over past year

### Origin of downloads

### Actions (login required)

View Item |