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.
Chinese traditional visual culture symbols (CT-VCSs) is formed in the tradition and has the characteristic of Chinese unique ideological and cultural connotation. It is a visual cultural heritage of Chinese culture. So the research on CT-VCSs has important practical significance. In this paper, it is mainly about the recognition and classification of CT-VCSs based on machine learning. We make use...
Globalization is a historic chance for China development. Moreover, Chinese traditional Visual Cultural Symbols (VCS) is a great tag of China. Image is a carrier of VCS. With the help of machine learning, we can recognize these VCS among numerous images very well. In this paper we propose combining with several features such as SIFT, HOG, RGB, LBP to describe an image and coding these features into...
With the explosive growth of information in dimension and magnitude, how to understand these complex data becomes a big challenge. Visualizing data with multivariate attributes is a hot research field in the information visualization domain. This paper makes a research of multivariate data visualization, and uses various attributes mapping method in visualizing movie network data for personalized...
In this paper, we study the effect of an entropy model in a watermarking system on two aspects: visual information measurement and united masking function. We propose a primal sketch based visual entropy model (short for PSVEM) for the watermarking system. The PSVEM is built on both image content analysis and hierarchical perception decomposition. Experimental results show that the digital watermarking...
How to extract the features quickly and correctly is the essential precondition for image identification and classification. As there existing large computation problems in the traditional feature extraction algorithms, this paper proposes a faster algorithm. Firstly, the image connected region is encoded by using the Vertex Chain Code to map as a closed area. Then a unified computational framework...
Information entropy is often applied as one of masking effect in digital watermarking system. At present, some scholars have used entropy masking to improve the performance of their watermarking algorithm. This paper mainly introduces the entropy masking model in three different domains, and gives experiment report about utilizing spatial domain, DCT domain, and DWT domain entropy masking model in...
In this paper, we consider the problem of automatic landmark image recognition. Specifically, we identify a fundamental issue that lurks in such applications as modern landmark recognition that arises as a natural consequence of a current state-of-the-art techinque, namely one-versus-all SVM. Then, we provide a unary classification approach that retains much of the benefits of one-versus-all SVM's...
Perceptual watermarking for video needs to take full advantage of the results of human visual system (HVS) studies. Just noticeable distortion (JND), which refers to the maximum distortion that the HVS does not perceive, gives us a way to model the HVS accurately. Since motion is a specific feature of video, estimation of the JND profile for video needs to take into account the temporal HVS properties...
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.