International Journal of Electrical, Electronics and Data Communication (IJEEDC)
eISSN:2320-2084 , pISSN:2321-2950
current issue
Volume-8,Issue-1  ( Jan, 2020 )
  1. Volume-7,Issue-12  ( Dec, 2019 )
  2. Volume-7,Issue-11  ( Nov, 2019 )
  3. Volume-7,Issue-10  ( Oct, 2019 )

Statistics report
Apr. 2020
Submitted Papers : 80
Accepted Papers : 10
Rejected Papers : 70
Acc. Perc : 12%
Issue Published : 85
Paper Published : 1402
No. of Authors : 3795
  Journal Paper

Paper Title
Extraction of Object Skeleton from Natural Images using Fully Convolutional Networks using Hierarchical Feature Integration

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

Author - Krunal Sapte, Jayeshree Kundargi

| PDF |
Viewed - 48
| Published on 2019-01-29
IRAJ Other Journals
IJEEDC updates
Volume-7,Issue-12(Dec,2019) Want to join us ? CLick here
The Conference World



Technical Editor, IJEEDC
Department of Journal and Publication
Plot no. 30, Dharma Vihar,
Khandagiri, Bhubaneswar, Odisha, India, 751030
Mob/Whatsapp: +91-9040435740