The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Despite remarkable progress of face analysis techniques, detecting landmarks on large-pose faces is still difficult due to self-occlusion, subtle landmark difference and incomplete information. To address these challenging issues, we introduce a novel recurrent 3D-2D dual learning model that alternatively performs 2D-based 3D face model refinement and 3D-to-2D projection based 2D landmark refinement...
Drift is the most difficult issue in object visual tracking based on framework of “tracking-by-detection”. Due to the self-taught learning, the mis-aligned samples are potentially to be incorporated in learning and degrade the discrimination of the tracker. This paper proposes a new tracking approach that resolves this problem by three multi-level collaborative components: a high-level global appearance...
It is quite challenging to monitor an ironmaking process due to some of its special characteristics such as lack of direct measurements and strong disturbances. Hence extracting robust features of the normal process from complex historical data is vitally important. Denoising autoencoder (dA), a recently developed deep learning technique, has become a popular tool to extract and compose robust features...
Robust scene recognition serves as an essential task for robots to work within a complex dynamic environment. Considering vision device's limited adaptability in the dark environment, a 3D-laser-based scene recognition approach that extracts and matches SIFT features from Bearing Angle images is proposed, which makes it possible to make full use of both global metric information and local scale-invariant...
A novel semi-fragile watermarking scheme in DWT domain for image authentication and tamper localization is proposed in this paper. The proposed scheme extracts content-based image features from the approximation subband in the wavelet domain to generate the watermark. Then the watermark is embedded into the middle frequency subband in the wavelet domain. For image authentication and tamper localization,...
In order to protect the copyright of digital productions, a novel watermarking algorithm based on phase congruency corner detection and Singular Value Decomposition (SVD) is presented. By introducing the phase congruency detects corners and edges method, the attacked watermarked image can be corrected and the watermark synchronization is realized. In this way, which are used for information hiding,...
In this paper, a novel gray-level image watermarking algorithm based on local feature region and Singular Value Decomposition (SVD) is presented for copyright protection. A new way which utilizes the Binary Coded Decimal (BCD) method and encodes the gray-level secret information into bit string is used. It employs the singular values of SVD to extract the most valuable features of the watermark image...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.