Search
Feedback
About UniCat 
Help
News
| Listing 1 - 3 of 3 |
Sort by
|
Book
ISBN: 7540204583 Year: 1992 Publisher: Beijing : Beijing yanshan chubanshe,
Abstract | Keywords | Export | Availability | Bookmark
Loading...Choose an application
- Reference Manager
- EndNote
- RefWorks (Direct export to RefWorks)
Dissertation
ISBN: 9789460185830 Year: 2012 Publisher: Leuven Katholieke Universiteit Leuven
Abstract | Keywords | Export | Availability | Bookmark
Loading...Choose an application
- Reference Manager
- EndNote
- RefWorks (Direct export to RefWorks)
Perceptual hashing is a solution for persistent content identification and robust content authentication. The principle of this technique is to extract robust and discriminative features from multimedia data. These features are resistant to incidental distortion, such as compression. They do not vary as long as the content is not significantly changed. They are converted into a compact perceptual hash (PH) value. In this thesis, we provide a comprehensive introduction to perceptual hashing, including the basic definitions, the application scenarios, the security aspects, the design principles, the performance metrics, etc. We clarify different application scenarios and security aspects. We focus on natural scene images and propose several PH algorithms with state-of-the-art performance. We propose three PH algorithms for image content identification. The first one is based on higher-order cumulants. The second one is based on regional features extracted by the angular radial transform. The third one is based on contour features extracted through edge detection. We also derive two video hash algorithms by extending the cumulant-based algorithm. One is suitable for partial video identification. The other is designed for complete video identification. We propose three PH algorithms for image content authentication. The first one is based on the phase of the discrete Fourier transform. The second one is a block-based extension of the first. It facilitates tamper location. The third one is based on the sign bits of a wavelet transform. It is jointly designed with a watermarking algorithm, and can be conveniently embedded in an image. We also propose a PH algorithm for image quality assessment, a framework for security enhancement, and two frameworks for video hash construction.
Book
Year: 2022 Publisher: New York : Association for Computing Machinery,
Abstract | Keywords | Export | Availability | Bookmark
Loading...Choose an application
- Reference Manager
- EndNote
- RefWorks (Direct export to RefWorks)
It is our great pleasure to welcome you to SUMAC 2022, the 4th edition of the ACM workshop on Structuring and Understanding of Multimedia heritAge Contents. The digitization of large quantities of analogue data and the massive production of born-digital documents for many years now provide us with large volumes of varied multimedia data (images, maps, text, video, multisensor data, etc.), an important feature of which is that they are cross-domain. "Cross-domain" reflects the fact that these data may have been acquired in very different conditions: different acquisition systems, times and points of view (e.g. a 1962 postcard from the Arc de Triomphe vs. a recent street-view acquisition by mobile mapping of the same monument). These data represent an extremely rich heritage that can be exploited in a wide variety of fields, from social science and humanities to land use and territorial policies, including smart city, urban planning, tourism, creative media and entertainment. In terms of research in computer science, they address challenging problems related to the diversity and volume of the media across time, the variety of content descriptors (potentially including the time dimension), the veracity of the data, and the different user needs with respect to engaging with this rich material and the extraction of value out of the data. These challenges are reflected in research topics such as multimodal and mixed media search, automatic content analysis, multimedia linking and recommendation, and big data analysis and visualization, where scientific bottlenecks may be exacerbated by the time dimension, which also provides topics of interest such as multimodal time series analysis.
| Listing 1 - 3 of 3 |
Sort by
|