Unsupervised Method of Object Retrieval Using Similar Region Merging and Flood Fill
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2011, Vol 2, Issue 9
Abstract
In this work; we address a novel interactive framework for object retrieval using unsupervised similar region merging and flood fill method which models the spatial and appearance relations among image pixels. Efficient and effective image segmentation is usually very hard for natural and complex images. This paper presents a new technique for similar region merging and objects retrieval. The users only need to roughly indicate the after which steps desired objects boundary is obtained during merging of similar regions. A novel similarity based region merging mechanism is proposed to guide the merging process with the help of mean shift technique. A region R is merged with its adjacent regions Q if Q has highest similarity with R among all Q’s adjacent regions. The proposed method automatically merges the regions that are initially segmented through mean shift technique, and then effectively extracts the object contour by merging all similar regions. Extensive experiments are performed on 22 object classes (524 images total) show promising results.
Authors and Affiliations
Kanak Saxena, Sanjeev Jain, Uday Singh
Keywords
Related Articles
- EP ID EP129647
- DOI -
- Views 153
- Downloads 0
Effective Calibration and Evaluation of Multi-Camera Robotic Head
The paper deals with appropriate calibration of multispectral vision systems and evaluation of the calibration and data-fusion quality in real-world indoor and outdoor conditions. Checkerboard calibration pattern develop...
Credit Card Fraud Detection using Deep Learning based on Auto-Encoder and Restricted Boltzmann Machine
Frauds have no constant patterns. They always change their behavior; so, we need to use an unsupervised learning. Fraudsters learn about new technology that allows them to execute frauds through online transactions. Frau...
Building a Robust Client-Side Protection Against Cross Site Request Forgery
In recent years, the web has been an indispensable part of business all over the world and web browsers have become the backbones of today's systems and applications. Unfortunately, the number of web application attacks...
Intellectual Paradigm of Artificial Vision: from Video-Intelligence to Strong Artificial Intelligence
A new (post-Shannon) informational approach is suggested in this paper, which allows to make deep analysis of nature of the information. It was found that information could be presented as an aggregate of quantitative (p...
SSL based Webmail Forensic Engine
In this era of information technology, email applications are the foremost and extensively used electronic communication technology. Emails are profusely used to exchange data and information using several frontend appli...