最新刊期
卷 4 ， 期 8 ， 1999
- 摘要：This paper makes an analysis on the data management of Geographical Information System (GIS). Besides of generally describing the nature and features of Data Warehouse, it explores the functionalities and features of Data Warehouse specified in Geographical Information System, and also delivers the infrastructure of Geographical Information System and addresses the pattern of shared resources based on Geographical Information System data warehouse, expecially discussing the key technologies throughout the process of it' s implementation.2534|131|0更新时间：2024-05-08
- 摘要：In this paper, a new image decoding algorithm to remove the“blocking artifact”appearing with block-transform coding is proposed. In the algorithm, the correlation between adjacent pixels is used to define smooth constraint convex sets. At the decoder, the blocky image is projected onto these convex sets by using the theory of project onto convex sets, and the ultimate result is a smooth image without block artifact. Experiments demonstrate that this new algorithm can not only make the decoded image more smoother but also maintain the details of the image.2268|131|0更新时间：2024-05-08
- 摘要：A dynamic segmentation of moving targets based on an active contour is presented in this paper.Utilizing that the active contour is a B spline curve, the way for design the num ber of controlpoints is given. Meanwhile, the motion of B spline controlpoints is derived from the im age data, so that the active contourcan track the edge of moving object automatically and dynamic segmentation is performed. Experimental results are also included to show the feasibility of the newly presented method.关键词：active contour;B spline;Edge tacking;Dynamic segmentation;AIC criterion3390|196|0更新时间：2024-05-08
- 摘要：Research on nonnoise coding method serving the needs of medicaldiagnosis is a new field in PACS,CT and MRI scanners provided lotsof 3D images everyday. In this paper, a three dimensionalm edical images compression method based on 3D wavelet transform is proposed.The 2D medicalim age group is regarded as 3D image. The authors expatiate on several questions which must be paid attention to in 3D wavelet transform, and an integrity 3D wavelet transform coding method is proposed.The experimental result shows this 3D coding method can offset the failure of2Dcoding method in PACS perfectly.2731|136|0更新时间：2024-05-08
- 摘要：In this paper,an adaptive image watermarking algorithm in DCT domain based on the block classification is proposed.By exploiting the visual masking features of HVS,the algorithm splits the original image into blocks and classifies these blocks.Watermark components with different strength are inserted into some low-frequency coefficients adaptively according to the clsaaification.The experimental results demonstrate that the watermarks generated with the proposed algorithm are invisible and robust against noise and commonly used image processing techniques.关键词：Image watermarking;digital watermarking;visual masking;Block classification;DCT3047|144|0更新时间：2024-05-08
- 摘要：The active contour model, as known as‘Snake’,is often used when one wanted to get a precise contour of an object in image processing field. The Snake algorithms known before often converge to a wrong result because they have not used the whole shape factor in the procedure of finding“minimum energy position”. This problem becomes more serious in some fast algorithms (these fast algorithms were usually obtained by decreasing the relation of Snake points). In this paper, a new active contour model based on a typical fast algorithm of Snake is proposed. Because the new algorithm considers the whole shape factor, the relationship among the Snake points is stronger than before and the reliability of computing result is improved. The effectiveness of the new algorithm is confirmed by the experiment in the end of this paper.关键词：Active contour model;Snake;Contour;Shape2156|138|0更新时间：2024-05-08
- 摘要：This paper proposes the adaptive directional filter, which is exploited for the extrac ting of left ventricular (LV) contour. This algorithm could produce the exact ridge point by applying directional filter with smoothing operator in the angiography images damaged by noise. The Edge Directional Vector as the result of this filter is efficient for predicting the edge ahead, while the filter parameters is adaptive. This proposed method provides the more precise and more automatic -extracting LV contour only with fewer interactives. The experimental results show that this proposed algorithm could improve the accuracy and reproducibility, and reduce the computational consumption remarkably.2269|140|0更新时间：2024-05-08
- 摘要：Hough transform is one of the most useful methods to detect the location of a certain mark whose type is already known. In this paper Hough transform is used to detect the circle mark on a printed circuit board in order to find the circuit error in the PCB inspection system.2913|159|0更新时间：2024-05-08
- 摘要：An edge detection method based on feed forward neural network and Hopfield neuralnetwork are proposed, the feed forward neural network is used to enhance and encode the information in the region of tested pixel, and its result is the input of Hopfield neural network which does iterative working till the network converges. The new neural network saves the computational cost and can generate edge map clearer than traditional Hopfield neural network. The whole system work sun der unsupervivsed leaning, so it is easy to train the neural networks.2529|143|0更新时间：2024-05-08
- 摘要：This paper presents a method using feed-forward three layers neural networks and computer vision technology to recognize automobile models. It includes automobile model image segmentation, character abstraction, automatic recognition and classification based on feed-forward three layers neural networks. All algorithms in this paper are verified at 586/ 133 computer and experimental results are efficient for recognition and classification.2297|131|0更新时间：2024-05-08
- 摘要：Mandelbrot' s fractal theory regards that many natural and medical images as the end result of Fractional Brownian Motion(FBM) . The fractal dimension is suit to measure the fineness or roughness of the surface.Based on this idea, the fractal dimension is applied in classifing ultrasonic images of muscle organ in this article. After the fractal dimensions of 60 sam- ples are calculated by this way ,then classified by Bayes classifier,the correct classification rate accounts to 88.33%。The very high rate provethat the fractal dimension can be a new feature for clinical diagnose and very significant to improve the correct diagnostic rate.2446|124|0更新时间：2024-05-08
- 摘要：This paper studies an images moother based on two dimensional discrete orthogonal wavelet transform. By thresholding the wavelet transform coefficients of noisy images, the original image can be reconstracted correctly. Simulations show this denoising method is valid.2150|117|0更新时间：2024-05-08
- 摘要：This paper gives a method of texture classification based on vectorquantization. By using vectorquatization to create the symbol images of original images,the cooccurences matrix of these symbol images can be gotten. Four digital features of cooccurences matrix are selected to obtain texture feature vectors of original images. Using the distance between two tex ture feature vectors as a matching standar, guick match and classification of texture images can be realized.2278|125|0更新时间：2024-05-08
- 摘要：By introducing the conceptofnode region, the global recognition approach focuses on the integral characters of the graphics in vectorization process of scanned image of engineering drawing. It depends on the connection between node region and segmentin acquiring the topologic structure of the graphics. And node regions can be used to separate the segments. The segment is recognized via tracing the chain code of its contour. The global recognition algorithm has such advantages as high speed, noise resistance.关键词：Global recognition;Integral characters;Segment following;Node region2589|172|0更新时间：2024-05-08
- 摘要：This article discusses analyzing curve shapeand distinguishing methods on 3D surface. Considering needs of recognizing 3D foot marks in detective work, this paper poses drawing features of equal value curves of three dimentional surface, the analysis for space structure and autoregresive spectrum of the curve shape,and a fuzzy distinguishing method on the base of the above analysis. It is proved by experiments that the method is very effective on recognizing 3D surface.关键词：Analyzing curve shape;Distinguishing 3D surface;Auto regresive spectrum;Fuzzy complex judgement2793|140|0更新时间：2024-05-08
- 摘要：Ridge Lines and ravine linesare extracted automatically from terrain contour map, by acquiring directionalderivations vertical with ridge line and ravine line with Fourier Transform in frequency (wave domain) domain.2654|166|0更新时间：2024-05-08
- 摘要：The method of data presentation and interpolation is a basic issue in 3D GIS, which will affect the management of spatial data and spatial analysis. It's a key problem for many functions of 3D GIS. Comparing several spatial data presentations, on the base of others research, the authors propose the simple based geospatial data presentation, abstract geoobjects as point, line, surface, and body. Then their logical design and topological relation are given. For visiualization and rebuilding of geoobject, simple based interpolation methods are introduced.3444|173|0更新时间：2024-05-08
- 摘要：A new method for interpolating 3D space curve with circular arc spline is introduced in this paper, the method is very robust for any 3D data sequences. The global G1 continuity can be achieved whether the spline is open orclosed.关键词：Space curve;Circular arc spline;G1 continuity;Closed space curve4159|141|0更新时间：2024-05-08
- 摘要：Triangular mesh structure isan important irregular mesh in data visualization. An effective way for reducing computation and memory requirements is to extract feature regions from massive data set, and only process (visualize, store, transmit, etc.) the data in these regions. For this reason, we give an algorithm for detecting edge points from triangular mesh data. The algorithm can be applied to adaptive subdivision of triangularm eshes.2670|143|0更新时间：2024-05-08
- 摘要：In this paper, we propose a mesh based method, which can directly operate(reshape) the free shape model stored in the computer database. By multiresolution, we can overcome of local and global reshape region problem. We also propose a high speed interference detection algorithm and a reshape algorithm needed in multiresolution. This method enhances the creativeness and production of the 3D modeling within 3D virtual space, and its effectiveness is proved through several experiments.2422|122|0更新时间：2024-05-08
- 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