Biometric Person Authentication such as face, fingerprint, palmprint and signature depends on the quality of image processing. When it needs to be done under a low-resolution image, the accuracy will be impaired. So h...
详细信息
In this paper, we propose a novel classification algorithm, called geometrical probability covering (GPC) algorithm, to improve classification ability. On the basis of geometrical properties of data, the proposed algo...
详细信息
While manifold learning algorithms can discover intrinsic low-dimensional manifold embedded in the high-dimensional Euclidean space, the discriminant ability of the low-dimensional subspaces obtained by the algorithms...
详细信息
3D models are a new kind of cross-media resource which can be frequently seen in the network. Since the amount of them is very huge now, content-based retrieval can help to recognize a certain object or retrieve simil...
详细信息
3D models are a new kind of cross-media resource which can be frequently seen in the network. Since the amount of them is very huge now, content-based retrieval can help to recognize a certain object or retrieve similar ones from the giant database. This paper presents a new method for deriving 3D moment invariants and uses them as shape descriptors for the representation of 3D models. They are insensitive to surface noise and can be used in pervasive environment conveniently. We also illustrate how to build up experimental system and simulate 3D shape retrieval in wireless environment
According to the railway transportation system＇s characteristics, a new cellular automaton model for the single- line railway system is presented in this paper. Based on this model, several simulations were done to i...
详细信息
According to the railway transportation system＇s characteristics, a new cellular automaton model for the single- line railway system is presented in this paper. Based on this model, several simulations were done to imitate the train operation under three working diagrams. From a different angle the results show how the organization of train operation impacts on the railway carrying capacity. By using the non-parallel train working diagram the influence of fast-train on slow-train is found to be the strongest. Many slow-trains have to wait in-between neighbouring stations to let the fast-train（s） pass through first. So the slow-train will advance like a wave propagating from the departure station to the arrival station. This also resembles the situation of a highway jammed traffic flow. Furthermore, the nonuniformity of travel times between the sections also greatly limits the railway carrying capacity. After converting the nonuniform sections into the sections with uniform travel times while the total travel time is kept unchanged, all three carrying capacities are improved greatly as shown by simulation. It also shows that the cellular automaton model is an effective and feasible way to investigate the railway transportation system.
Currently in the community of medical imaging computation and analysis, there exist several excellent toolkits for various tasks. For example, VTK (http://***) is the most famous visualization tool and ITK (http://***...
详细信息
Currently in the community of medical imaging computation and analysis, there exist several excellent toolkits for various tasks. For example, VTK (http://***) is the most famous visualization tool and ITK (http://***) plays an important role in the segmentation and registration of medical images. These toolkits can assist the doctors to get the more accurate diagnosis, and help the researchers to get the more powerful capability of medical image processing. However, they are separate and style-various. Even for VTK and ITK, which are designed by the same company, users have to familiarize the two completely different coding styles. In this situation, using all of these toolkits is difficult. In this study, we will introduce 3D medical imaging computation and analysis platform (3DMed), which provides powerful functions such as image preprocessing, virtual cutting, surface rendering, volume rendering, manipulation and virtual endoscopy. The functional module description, system design and the visualization algorithm is demonstrated. The system can be widely applied to processing and analysis of CT and MR images.
In MR imaging, image noise, bias field, and partial volume effect are adverse phenomena that increases inter-tissue overlapping and hampers quantitative analysis. This study provides a powerful fully automated classif...
详细信息
ISBN:
(纸本)0769525210
In MR imaging, image noise, bias field, and partial volume effect are adverse phenomena that increases inter-tissue overlapping and hampers quantitative analysis. This study provides a powerful fully automated classification method, which combines the bias field correction and PV segmentation together. The method has been validated on simulated and real MR images for which gold standard segmentation available. The experimental results show that the proposed method is more accurate and robust than currently available models
This paper analyzes when a Hopf bifurcation occurs for a class of delay differential systems, and constructs the algorithms for determining the bifurcation's occurrence. By using some algebraic criteria, the "...
详细信息
This paper analyzes when a Hopf bifurcation occurs for a class of delay differential systems, and constructs the algorithms for determining the bifurcation's occurrence. By using some algebraic criteria, the "complete discrimination system for polynomials" and Hurwitz criterion, on-line determining bifurcation's occurrence can be realized. The methods unify and generalize the relevant results in the literature.
暂无评论