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.
A method for 3D human body modeling from a set of 2D images is proposed. This method is based upon the deformation of a predefined generic polygonal human mesh towards a specific one which should be very similar with the subject when projected on the input images. Firstly the user defines several feature points on the 3D generic model. Then a rough specific model is obtained via matching the 3D feature...
A novel stroke based sparse hybrid convolutional neural networks (CNNs) method is proposed for author classification of Chinese ink-wash paintings (IWPs). As Chinese IWPs usually have many authors in several art styles, this differs from real images or western paintings and has led to a big challenge. In our work, we classify Chinese IWPs of different artists by analyzing a set of automatically extracted...
In this paper we proposed a scalable interactive system for fresco deterioration detection by hyper-spectral image data analysis. The system integrates data mining and visualization algorithm and process the hyper-spectral big data from fresco efficiently and conveniently. Firstly, a Geospatial Data Abstraction Library (GDAL) is adapted which provides data reading, image preview and cropping functions,...
Classification of micro calcification clusters is very essential for early detection of breast cancer from mammograms. In this paper, an improved support vector machine (SVM) scheme is proposed, where optimized decision making is introduced for effective and more accurate data classification. Experimental results on the well-known DDSM database have shown that the proposed method can significantly...
Based on the idea of components and multi-layer rendering, a Chinese Ink-Wash painting styled 3D rendering algorithm is put forward which covers the simulation of brush styles and painting composition styles. We abstract some special renders, and each of them represents a kind of special art effect. Components of the input object model could be rendered and blended by multiple renders. During the...
The effect of stains on the cloth is one of the most common effects in animation and virtual world. Based on the in-depth study of the various characteristics of fabrics and dirt, a real-time simulation algorithm for stain on cloth is proposed. The LBE method is used to simulate surface flow, while the inner fabric transmission applied the Poiseuille viscose flow law. As rendering arithmetic, we use...
To model a high-resolution 3D human body model based on a set of image is a challenge work. In this paper, we present the 3D human body model reconstructed technique based on a generic model deformation method and a color texture standardization technique. Firstly a set feature points on images and their corresponding character vertices on generic model are defined. Then a customized model is yielded...
Diffusion and superposition are the most important and complicated artistic effects in computer simulation of Chinese ink-wash drawing. This paper proposes a physical-based simulation method, which is grounded on the diffusion-effect model. First we establish particle movement equations to calculate the diffusion amount of water-ink particles according to Brownian motion and Capillary effect. In the...
Flow motion on curve surfaces of arbitrary topology is an interesting visual effect but a complex dynamics to simulate. In this paper, we introduce a novel and effective way to modal such dynamics. We propose a technique that adapts a unstructured lattice Boltzmann model (Unstructured LBM). The whole algorithm consists of five aspects, including surface modeling with unstructured triangular meshes,...
For purposes of intelligent art creation and existed painting style reusing, we presents a neural network-based Chinese ink-painting art style learning method, which is quite different from the traditional “pixel-wise” or “sample-wise” style transferring work. We first give a generalized definition for style features of Chinese ink painting, and then establish the style learning mechanisms with combination...
A novel system for automatic three-dimensional ink-style rendering is presented. The goal for the whole is to transmit the Chinese painting style to three-dimension models. In this system, the input artwork is first segmented into several regions used for modeling and artistic style analysis: (1) region contours and skeletons is found to build three-dimension models by surface inflation technique,...
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.