Improved technique for object detection using Similarity Based Region Merging
Journal Title: International Journal of Research in Computer and Communication Technology - Year 2013, Vol 2, Issue 5
Abstract
object segmentation is an important task in image processing and computer vision. We address a method to effectively discover a user’s concept when object of interest are involved in input image. In this paper our method corporate frameworks for object retrieval using semi-automatic method for object detection because fully automatic segmentation is very hard for natural images. To improve the effectiveness of region merging we propose a new similarity based object retrieval. The users only need to roughly indicate the after which steps desired objects closed contour is obtained during the automatic merging of similar regions. A similarity based region merging mechanism is proposed to guide the merging process with the help of initial segmentation technique. Any two or more regions are merged with its adjacent regions on the basis of similarity. The proposed method automatically merges the regions that are initially segmented through initial segmentation technique, and then effectively extracts the object contour by merging regions.
Authors and Affiliations
Garima Singh Rawat, Joy Bhattacharjee, Roopali Soni
Keywords
Related Articles
- EP ID EP27580
- DOI -
- Views 357
- Downloads 5
Android Application Based Optical Character Recognition For Malayalam Language
Optical character recognition is to recognize alphanumeric or other characters from a digital image. At first the document to be converted will be captured by mobile camera or scanner then the resultant text will be ava...
Improved Fused Floating Point Add-Subtract Unit
This paper presents improved architectures for a fused floating -point add–subtract unit. The fused floating -point add–subtract unit is useful for digital signal processing (DSP) applications such as fast Fourier tr...
Technical Survey of Heart of Propagation Models: A Spectrum Analysis
In this paper, we exhibit a sneak peak of dynamic spectrum access approaches. Different methodologies foreseen for dynamic spectrum access a r e expansively characterized under three models: selective model, impartin...
Performance Analysis of AOMDV, OLSR and DSR Routing Protocols Using UDP agents in MANETS
Mobile Ad hoc Network is a collection of mobile nodes that dynamically form a temporary network and are capable of communicating with each other without the use of a network infrastructure or any centralized administ...
Episodic Reinforcement- Clustering technique (ERCT) based POPTVR and Modified POPTVRFNN for pattern classification
In general, a Fuzzy Neural Network (FNN) is characterized by its learning algorithm and its linguistic knowledge representation. However, it does not necessarily interact with its environment when the training data i...