Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Shijie Zhang"'
Publikováno v:
ICCV Workshops
In this paper, we focus on training a deep neural network to in-paint and restore the historical painting of Dunhuang Grottoes. Dunhuang Grottoes is more than 1000 years old and the wall-painting on the grottoes has suffered from various deterioratio
Publikováno v:
ICIP
Stereo image applications are becoming more and more prevalent. However, there has been little research on stereo image enhancement. In this paper, we address the challenging problem of underwater stereo image enhancement. A new underwater imaging mo
Publikováno v:
ICME
As the increasing popularity of superpixel-based applications, measuring superpixel-level similarity becomes an important and commonly required problem. In this paper, we propose a general bag of squares (BoS) model for such particular purpose. Compa
Publikováno v:
2012 IEEE 11th International Conference on Signal Processing.
To solve the problems of difficulty in denoising of aero-optical degraded image due to aero-optical effects, a denoising algorithm based on improved Nonsubsampled Contourlet transform(NSCT) is proposed. Firstly, improved NSCT disassembly was construc
Publikováno v:
FSKD
A new matching method based on improved Nonsubsampled contourlet transform (NSCT) is put forward to solve the problem of low matching precision in matching of infrared and visible images. Firstly, improved NSCT is introduced; then, improved NSCT disa
Autor:
RongBao Chen, ShiJie Zhang
Publikováno v:
2010 International Conference on Mechanic Automation and Control Engineering.
In this paper, face recognition technology is applied to automotive security. Because the face system is totally non-intrusive, it can therefore make an existing security system more effective without bothering the user in any way. This paper introdu
Publikováno v:
2009 Fourth International Conference on Innovative Computing, Information and Control (ICICIC).
Jsteg and F5 are two typical steganography methods of JPEG images and have been used widely. To distinguish F5 stego images and Jsteg stego images, a classification algorithm based on sensitive features and SVM classifier is presented, where the sens
Autor:
Fred Stentiford, Shijie Zhang
Publikováno v:
CBMI
A novel three-stage framework for object tracking under stationary background conditions is proposed in this paper. The first stage uses an attention based method to extract motion information. The second stage then applies a region growing and match
Autor:
Shijie Zhang, Fred Stentiford
Publikováno v:
ICIP (3)
Motion detection and estimation are known to be important in many automated surveillance systems. It has drawn significant research interest in the field of computer vision. This paper proposes a novel approach to motion detection and estimation base