• Aug 08, 2022 News![International Journal of Computer Theory and Engineering] Accepted for Coverage in Scopus   [Click]
  • Dec 30, 2021 News!Vol.13, No.1 & Vol.13, No.2 have been indexed by Inspec.   [Click]
  • Jul 15, 2022 News!IJCTE Vol.14, No.3 has been published.   [Click]
General Information
Editor-in-chief
Prof. Mehmet Sahinoglu
Faculty at Computer Science Department, Troy University, USA
I'm happy to take on the position of editor in chief of IJCTE. We encourage authors to submit papers concerning any branch of computer theory and engineering.

International Journal of Computer Theory and Engineering (IJCTE) is an international academic open access journal which gains a foothold in Singapore, Asia and opens to the world. It aims to promote the integration of computer theory and engineering. The focus is to publish papers on state-of-the-art computer theory and engineering. Submitted papers will be reviewed by technical committees of the journal and association. The audience includes researchers, managers and operators for computer theory and engineering as well as designers and developers.
 
All submitted articles should report original, previously unpublished research results, experimental or theoretical, and will be peer-reviewed. Articles submitted to the journal should meet these criteria and must not be under consideration for publication elsewhere. Manuscripts should follow the style of the journal and are subject to both review and editing.

Important Notice: IJCTE will only accept new submissions through online submission system.
Featured Article

Internet of Things: Financial Perspective and Associated Security Concerns

Bilal Ahmad Pandow, Alwi M Bamhdi, and Faheem Masoodi
The internet of things (IoT) has grown at a significant pace and has revolutionized the whole technological aspects of internet and things. In the paper around 800 IoT companies headquartered in various countries globally were analyzed. It was observed that the financial returns of select IoT companies for past five years have witnessed a decent growth however; the industry witnessed a slight dip in the year 2016......   [Read More]


Copyright © 2008-2022. International Association of Computer Science and Information Technology. All rights reserved.
 Accurate Silhouette Extraction of a Person in Video Data by Shadow Evaluation - Volume 6, Number 6 (Dec. 2014) - IJCTE
  • Aug 08, 2022 News![International Journal of Computer Theory and Engineering] Accepted for Coverage in Scopus   [Click]
  • Dec 30, 2021 News!Vol.13, No.1 & Vol.13, No.2 have been indexed by Inspec.   [Click]
  • Jul 15, 2022 News!IJCTE Vol.14, No.3 has been published.   [Click]
General Information
Editor-in-chief
Prof. Mehmet Sahinoglu
Faculty at Computer Science Department, Troy University, USA
I'm happy to take on the position of editor in chief of IJCTE. We encourage authors to submit papers concerning any branch of computer theory and engineering.

IJCTE 2014 Vol.6(6): 476-483 ISSN: 1793-8201
DOI: 10.7763/IJCTE.2014.V6.913

Accurate Silhouette Extraction of a Person in Video Data by Shadow Evaluation

Zhengping Wang, Bok-Suk Shin, and Reinhard Klette
Abstract—This paper presents a new shadow detecting method for silhouette extraction of a person in gray-level video sequences. We use a shadow evaluator to verify each raw shadow pixel that was detected by Gaussian distribution analysis. The evaluator considers a raw shadow pixel initially to be a fake shadow pixel, and marks it as a silhouette pixel if it is enclosed or semi-enclosed by moving occlusion boundaries of a person. Those were extracted by subtracting edges in the current frame from edges of the background. We also propose a silhouette compensation technique to recover some missing (i.e. removed) silhouette pixels by using a similarity criterion between silhouette pixels and their neighbors. Experimental results show us that the proposed algorithm keeps a silhouette of a person more accurate compared to other methods. Methods advocated by other researchers in YUV or RGB color space, typically remove silhouette pixels as shadow if the color of these pixels is similar to that of the surrounding background.

Index Terms—Shadow removal, silhouette detection, shadow evaluator, silhouette compensation.

The authors were with the University of Auckland, New Zealand (e-mail: wzhengping@gmail.com).

[PDF]

Cite:Zhengping Wang, Bok-Suk Shin, and Reinhard Klette, "Accurate Silhouette Extraction of a Person in Video Data by Shadow Evaluation," International Journal of Computer Theory and Engineering vol. 6, no. 6, pp. 476-483, 2014.


Copyright © 2008-2022. International Association of Computer Science and Information Technology. All rights reserved.