Color Segmentation by Relationship Trees and Consequent Tree Matching
Volume: 5 - Issue: 08 - Date: 01-08-2016
Approved ISSN: 2278-1412
Published Id: IJAECESTU284 | Page No.: 1201-1204
Author: Ankit Bihone
Co- Author: Mr. Imran Khan
Abstract:-In this work, we tend to review a model of a content-based image retrieval system by
using the new set up of mixing color segmentation by relationship trees and a consequent treematching methodology. We tend to retain the hierarchical relationship of the world during a
illustration throughout segmentation. Using the info of the relationships and options of the
regions, we'll represent the specified objects in pictures further accurately. The approach depends
on the key ideas of matching a part template tree to pictures hierarchically to generate a reliable
set of detection hypotheses and optimizing it through global chance re-evaluation and fine
occlusion analysis.
Key Words:-Image segmentation, hierarchical merge tree, constrained conditional model, supervised Classification, object-independent, ensemble model
Area:-Engineering
Download Paper:
Preview This Article
