DOIONLINE

DOIONLINE NO - IJEEDC-IRAJ-DOIONLNE-14226

Publish In
International Journal of Electrical, Electronics and Data Communication (IJEEDC)-IJEEDC
Journal Home
Volume Issue
Issue
Volume-6,Issue-11  ( Nov, 2018 )
Paper Title
Extraction of Object Skeleton from Natural Images using Fully Convolutional Networks using Hierarchical Feature Integration
Author Name
Krunal Sapte, Jayeshree Kundargi
Affilition
M.Tech. Student, K.J Somaiya College of Engineering Department of Electronics and Telecommunication, Vidyanagar, Mumbai, Maharashtra, India Associate Professor, K.J Somaiya College of Engineering Department of Electronics and Telecommunication, Vidyanagar, Mumbai, Maharashtra, India
Pages
16-20
Abstract
Object representation and object detection requires object skeleton as they are supplementary to the object outline to give more data, like how object scale deviates amid different parts of object but extracting skeleton of objects from images which are natural is very tedious because the thickness of object skeleton may dramatically vary among different objects. We present a fully convolution neural network architecture by introducing hierarchical feature integration mechanism to address the skeleton detection problem. The proposed approach has a strong multi-scale feature integration ability that intrinsically captures high level semantics from deep layers as well as lower level details from shallow layers. The hierarchal integration of different CNN feature levels enables mutual refinement across features of different layers and possesses good ability to capture rich object context and high resolution details. The proposed method was evaluated on SK-Large and Sympascal database. Keywords - Convolutional Neural Network, Hierarchical Feature Integration Mechanism, Object Skeleton
  View Paper