Non-photorealistic rendering (NPR) such as stylization has received much concern in area of computer graphics and imageprocessing. In this paper, a simple and effective method is proposed for streamline stylization. ...
详细信息
A method for zip code recognition is presented. 2D binary images are input to HAVNET, a neural network which employs the Hausdorff distance as a similarity metric to train the weights which are required to represent t...
详细信息
An efficient framework utilizing both local features and geometrical distribution for detecting facial components is presented. First, candidate facial components are efficiently collected by cascaded boosting of Haar...
详细信息
In this paper, we describe an experimental investigation to evaluate the significance of different facial regions of a person in the task of gender classification. For this purpose we use a Support Vector Machine (SVM...
详细信息
Segmentation of connected handwritten Chinese characters is a very difficult task in document image analysis. In this paper, a novel algorithm based on stroke analysis and background thinning is proposed to segment co...
详细信息
CT scans are an exceptional tool for quantitative airway analysis. Due to the complex voxel connectivity and branch structure of the airway, precise and fine segmentation results are difficult to accomplish. We propos...
详细信息
We present a method for recovering 3D shapes of deformable surfaces from monocular image sequences. State-of-the-art methods on this problem [1] utilize L∞-norm of reprojection residual vectors and formulate the trac...
详细信息
Faults of sensor data will always present in sensor networks because of unreliable communication links, measurement interference and harsh environment. Developing fusion algorithms that can tolerate faults is necessar...
详细信息
ISBN:
(纸本)9781849191388
Faults of sensor data will always present in sensor networks because of unreliable communication links, measurement interference and harsh environment. Developing fusion algorithms that can tolerate faults is necessary for reliable sensor network applications. In this paper, we study the fault tolerant fusion for moving vehicle classification based on Marzullo's interval fusion algorithm. The unreliable sensor data are represented using interval estimations. To reduce communication cost, quantized interval representation is adopted. Simulation results demonstrate the validity of the interval fusion algorithm. By using quantized representation, the communication cost is reduced.
An X-ray tube spectra measuring method is presented in this paper. The measurement is accomplished by reconstruction from attenuation data based on a nine-parameter tungsten anode X-ray spectral model. The proposed mo...
详细信息
ISBN:
(纸本)0819461857
An X-ray tube spectra measuring method is presented in this paper. The measurement is accomplished by reconstruction from attenuation data based on a nine-parameter tungsten anode X-ray spectral model. The proposed model is derived from a physical basis and composed of three parts: bremsstrahlung spectra, photoemission attenuation by X-ray tube inherent and added filter, characteristic radiations denoted by four Dirac delta functions. Firstly, for simplicity, the four characteristic radiations of the spectra model are merged into two according to a reasonable hypothesis. Secondly, the spectra reconstruction based on the modified model is carried out by calculating the model parameters from measured attenuation data. To further improve stability, two kinds of materials are used as the attenuators. Experiments show that this method can reach high precision and is insensitive to the noise in measured attenuation data. From the 10 measured attenuation data (7 from Al, and 3 from Copper) with 5% Poisson noise added, the precision of the reconstructed spectra can reach 98.56% for the 70kVp X-ray tube with tiny characteristic radiation, and 98.24% for the 120kVp X-ray tube with characteristic radiation. Spectrum is the characteristic of X-ray tube and widely used for many purposes. In engineering, the spectrum is mostly reconstructed from attenuation data, which is an ill-posed problem in mathematics. The method we presented with the features of including characteristic radiation, insensitive to noise and demanding fewer attenuation data will help to solve this problem perfectly.
Parallel coordinate descent algorithms emerge with the growing demand of large-scale optimization. In general, previous algorithms are usually limited by their divergence under high degree of parallelism (DOP), or nee...
详细信息
暂无评论