Please use this identifier to cite or link to this item:
http://dspace.dtu.ac.in:8080/jspui/handle/repository/15526
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | WADHWA, RESHAM | - |
dc.date.accessioned | 2017-01-24T09:10:15Z | - |
dc.date.available | 2017-01-24T09:10:15Z | - |
dc.date.issued | 2015-07 | - |
dc.identifier.uri | http://dspace.dtu.ac.in:8080/jspui/handle/repository/15526 | - |
dc.description.abstract | Swarm Intelligence uses a set of particles that move through the given search space and gather local information. This limited memory of particles is then used for solving problems. In this paper, we present algorithms based on the swarm intelligence based technique - the firefly algorithm. To generate boundaries, extra particles are removed by applying an appropriate threshold mechanism. In ACO, ants are distributed throughout the image and the movement takes place on the basis of pheromones, heuristics and the probability value. In the proposed firefly algorithm for Boundary Detection, fireflies are distributed in an image and the movement towards the solution depends upon the brightness and attraction amongst the fireflies. These algorithms’ performance is evaluated using Berkeley Segmentation DataSet (BSDS) and is compared with those of existing boundary detection algorithms via BSDS benchmark. | en_US |
dc.language.iso | en | en_US |
dc.relation.ispartofseries | TD NO.2670; | - |
dc.subject | SWARM OPTIMIZATION | en_US |
dc.subject | BOUNDARY DETECTION | en_US |
dc.subject | SWARM INTELLIGENCE | en_US |
dc.subject | BSDS | en_US |
dc.title | SWARM OPTIMIZATION ALGORITHM FOR BOUNDARY DETECTION IN IMAGES | en_US |
dc.type | Thesis | en_US |
Appears in Collections: | M.E./M.Tech. Computer Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Thesis Front (1).pdf | 234.26 kB | Adobe PDF | View/Open | |
Thesis Content (2).pdf | 2.03 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.