File(s) not publicly available

Position gradient and plane consistency based feature extraction

conference contribution
posted on 07.03.2018, 00:00 by Sujan ChowdhurySujan Chowdhury, Brijesh VermaBrijesh Verma, Ligang ZhangLigang Zhang
© Springer International Publishing AG 2016.Labeling scene objects is an essential task for many computer vision applications. However, differentiating scene objects with visual similarity is a very challenging task. To overcome this challenge, this paper proposes a position gradient and plane consistency based feature which is designed to distinguish visually similar objects and improve the overall labeling accuracy. Using the proposed feature we can differentiate objects with the same histogram of the gradient as well as we can differentiate horizontal and vertical objects. Integrating the proposed feature with low-level texture features and a neural network classifier, we achieve a superior performance (82%) compared to state-of-the-art scene labeling methods on the Stanford background dataset.

Funding

Category 1 - Australian Competitive Grants (this includes ARC, NHMRC)

History

Editor

Akira H; Seiichi O; Doya K; Kazushi I; Minho L; Derong L

Volume

9948 LNCS

Start Page

673

End Page

681

Number of Pages

9

Start Date

16/10/2016

Finish Date

21/10/2016

eISSN

1611-3349

ISSN

0302-9743

ISBN-13

9783319466712

Location

Kyoto, Japan

Publisher

Springer

Place of Publication

Cham, Switzerland

Peer Reviewed

Yes

Open Access

No

Author Research Institute

Centre for Intelligent Systems

Era Eligible

Yes

Name of Conference

International Conference on Neural Information Processing, 23rd, (ICONIP 2016) 2016