最新刊期
卷 10 ， 期 5 ， 2005
-
-
-
- 摘要：Because of the unique property in pattern recognition and in regression analysis, support vector machine(SVM) has become the topic of research recently. The advantages of SVM mainly lie in its capabilities of processing non-linear and highly dimensional data problems. Unextended SVM is very suitable for solving two-class classification problems. For multi-class classification, however, it should be converted into many of two-class classification problems, and can be constructed many of two-class classifier correspondingly. But the case results in more complexity of classifier structure, and so leads to decrease of decision speed. In order to get a fast classification, a new multi-class classifier with simplified structure is put forward so that the number of subclassifiers and decisive time are reduced greatly. The accuracy and complexity are also contrastively analyzed here. The validity of the new classifier is proved by simulated experiments.2782|185|0更新时间：2024-05-07
- 摘要：In surface reconstruction, the actual surface model generally contains several surface geometrical features. Namely it consists of multi-surface patches. If directly fitting surface with these point cloud data obtained from a laser scanner, the surface model presentation and the surface fitting are hard to do. Even it is difficult to use a simple formula to describe the surface model. In this paper, a method for region segmentation algorithm according to the curvature variation of data points is proposed. The operational principle is to calculate the curvature values to data points on each scanning line. The points with bigger curvature variation are picked up as boundary points. After borderline are determined, point cloud data are divided into several regions. Each region has simple geometrical features, and can be described in simple mathematical model, and then a single surface is reconstructal. This algorithm is simple, and can be easily understood and programmed. Efficiency of surface model reconstruction is enhanced.3540|201|0更新时间：2024-05-07
-
-
-
- 摘要：In surveillance system, moving target detection in image sequence is a very significant and difficult problem. The objective of this research was to present a new detection method to enhance the efficiency and accuracy of moving target recognition,and to resolve the difficulties brought by target distortion. The detail theory and algorithm of a new detection method, which was based on the lifting scheme of wavelet and deformable template technique, were described. The multi-scale images were used to improve the target matching efficiency, and the deformable templates were used to tracking the target distortions. The results indicated that the moving objects detected by the new method based on the lifting scheme were more robust than those detected by traditional methods. In addition, the detection speed became more rapid. The results seem to suggest that the new method be with efficiency and accuracy advantages in computer version.2446|193|0更新时间：2024-05-07
- 摘要：Images with geometrical distortions, which are taken by cameras, must be corrected before being analyzed. According to the normal distortion correction method for distorted images which obtains distortion coefficients by setting up a distortion model, but as the calculation is complicated and numerical error becomes a big problem, a distortion correction method based on neural networks is put forward in this paper. First of all, the sample coordinates which serve as input parameters of neural networks are extracted from a distorted template image by image processing technique. Then the neural networks are trained by samples. The trained neural networks can learn any distortion relationship between the normal image and the distorted image. Experiments are done by the new method in this paper, and the correcting results are given and analyzed. The experimental results show the neural networks distortion correction technique is satisfactory and it is used in the vision system of the welding robot.3066|202|0更新时间：2024-05-07
- 摘要：This paper expounds the fundamental theory of map projection and projection transformation,and analyzes the requirement of raster picture projection transformation and the characteristics differing from vertex projection transformation. The arithmetic of picture projection transformation and its optimization methods are emphasized. The authors take Visual C++ as software platform and develop the system of raster picture projection transformation.2749|210|0更新时间：2024-05-07
- 摘要：A large number of gray image are created and available on the Web, since more and more gray images and digitizing tools are developed for different applications. The techniques for content-based gray image retrieval is necessary. In gray image retrieval system, we propose multiscale generic Fourier descriptor(MGFD), which integrates generic fourier descriptor with multiscale anslysis.The experimental results show that MGFD is not only capable of multiscale anslysis, but robust against noise and other changes of image and it is also invariant to rotation and scale. It have a precise result in gray image retrieval.2990|226|0更新时间：2024-05-07
- 摘要：Image compressed techniques are very important for the storage, transportating, and processing of remote sensing data. The quality of a compressed image is directly related to its value in practice. Therefore, the authors introduced a several quality assessment indexes and the relevant concepts for compressed remote sensing image data. And then the constructing theories and basic algorithms for some indexes, such as compression rate, the quality of the compressed image, compression velocity, and complexity of the algorithm, are discussed in detail. The corresponding software for the quality prognosis of a compressed remote sensing date is developed.2676|178|0更新时间：2024-05-07
- 摘要：The Land Resource Satellites continuously send the remotely sensed data to the earth, so large quantity of data has been acquire by the satellite receiving ground station. Unfortunately, because of lacking the effective techniques for data mining and knowledge discovering from the polygenetic remotely sensed data, the majority of the useful information existed in the remotely sensed data not has been fully exploited. Researching the data mining and knowledge discovering technologies, especially suitable to the polygenetic remotely sensed data, through innovating and improving the traditional data mining and knowledge discovering technologies, can promote the level of automatically and intelligently interpreting the polygenetic remotely sensed data,and exploit the useful information existed in the remotely sensed data as much as possible. Basing on the traditional data mining and knowledge discovering technologies, the authors had investigated the technology flowing chart of the remotely sensed data mining and knowledge discovering procedure, and then designed the technological framework of the remotely sensed data mining and knowledge discovering system, finally proposed the prototype of the system. So the technological foundation for further developing the polygenetic remotely sensed data mining system had been established.3707|210|0更新时间：2024-05-07
- 摘要：As information descric the characteristics of spatial entities, spatial data is regarded as the most important part in the whole geographic information system. It is very significant to research the accessing methods of spatial data. In this paper, the authors discussed some problems of implementing Java-Based WebGIS. First, the authors investigate of the storage format of spatial data,then discussed the process of how to utilize the network advantages of Java language to implement the access of spatial data through Internet, and how to set up Java Applet to display the map, and finally developed a simple WebGIS using Java.2561|186|0更新时间：2024-05-07
- 摘要：In order to construct a new practical and fast iterative image reconstruction method, the ordered subsets(OS) technique is combined with the least square(LS) reconstruction of images in medical tomography. Reconstruction of simulated data and real positron emission tomography(PET) data shows that so accelerated OS-LS iterative image reconstruction method has a rapid convergent speed and higher spatial resolution. The reconstructed image quality and convergence speed by different subsets order are studied. As compared to the traditional LS reconstruction, OS-LS is L times faster, where L is the number of subsets, and the reconstructed images by OS-LS are better than the conventional FBP (filtered back-projection) as well. The conclusion is that the so proposed OS-LS reconstruction method can be used in real PET image reconstruction.2803|204|0更新时间：2024-05-07
-
- 摘要：Through close observation and research on the morphological formation, as well as growth rules of corn leaf, and combined with some knowledge in agriculture the mathematic model for changes on morphology in corn leaf was brought forward. By the meanings of techniques of Computer Graphics, VC++ and OpenGL, the 3-Dimensional Visualization of leaf morphological formation was realized on computers. The advantages of the model are as follows: the structure is simple, it is apt to be interactive, the images produced on computer with the model has high Sense of reality; and it can simulate the growing process of the corn leaf very well on computer.2811|182|0更新时间：2024-05-07
-
-
- 摘要：This paper proposes an algorithm of chaotic images scrambling based on the sort transformation. The new algorithm obtains the address codes of the images transposition by the sort transformation of the chaotic sequence and does not need the quantification. The probability density function of the chaotic orbits must be known by the method of quantification. The new algorithm, however, overcomes this disadvantage, which not only facilitates the choice of chaotic systems but also reduces the time complexity of traversing the images scrambling quantified by chaos. As a result, it increases the speed of scrambling images. Due to the strong irregularity of sort transformation, the new chaotic images scrambling algorithm possesses high-level security. The paper also analyzes the scrambling performance of the new algorithm in a statistical way. The results of the analysis indicate that the algorithm bears nice scrambling capability and guarantees the security of the encrypted images effectively.2651|202|0更新时间：2024-05-07
- Postal code：100190
- Tel：010-58887035/58887030/58887418 Email：jig@aircas.ac.cn
- Technical support is provided by Beijing Founder electronics co., LTD 京ICP备05080539号-4
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
0