最新刊期
卷 5 ， 期 9 ， 2000
- 摘要：This paper analyses the research platforms, methods and techniques of spatial analysis databases, as well as the advantages and disadvantages of various research platforms. And it discusses emphatically the spatial data types based on the Realms, ROSE algebra, and the research methods and techniques of spatial analysis databases based on extensible DBMS as well as the disadvantages and problems of the systems based on the principles. The Realms can be used to represent spatial data of two dimensions and to implement the spatial topological algorithms efficiently. First, the spatial subsystem based on the techniques of main memory databases and the ROSE algebra is designed and implemented. Then it is integrated into extensible DBMSs, or DBMSs with the ADT mechanism. And it is an efficient approach to develop spatial analysis database management systems.关键词：spatial databases;ROSE algebra;Spatial data types;Spatial analysis operators1956|130|0更新时间：2024-05-08
- 摘要：This paper is a review of literatures about the methods of image coding combining wavelet and fractals. After collecting and reading a lot of papers on image coding combining wavelet and fractals, we present a complete and detailed review of this field, including its status and possible future. Through ten years of research, wavelet image coding has been ripe for practice and may be accepted by some international standards of image coding. These standards are expected to come soon. Fractal image coding, however, is still under academic research. Combination with wavelet image coding may be a way out for fractal image coding from academic research to practical application.关键词：Wavelet image coding;Fractal image coding;Image coding combining wavelet and fractals1888|144|0更新时间：2024-05-08
- 摘要：This paper discusses the symmetric periodic extension method, which can be used to extend the finite length signal before filtering in the wavelet transform image coding. This method can avoid the expansion of subband image size and achieve perfect reconstruction. The odd and even length filters use different method to extend the signals.关键词：wavelet transform;Image coding;Boundary extension;Periodic extension;Symmetric periodicextension3078|121|0更新时间：2024-05-08
- 摘要：To improve the performance of algorithm, theory of fractal is applied in fields of image registration in this paper. The algorithm improved by unitized covered carpet is provided, and registration probability and speed are improved effectively. The paper also presents the method of calculating fractal character. Through simulation and compared with MAD, the algorithm demonstrates its satisfying effect and value to image registration.关键词：Carpet covered algorithm;Fractal character;Image registration2023|136|0更新时间：2024-05-08
- 摘要：In order to resolve the problem of image feathering in the region, the formula of weight function is presented based on the depth information of the region and every pixel in the region is processed according to the weight. As a result, the closer the pixel is to the region boundary, the less the correction of pixel value is, and the farther the pixel is to the region boundary, the more the correction of pixel value is. This method of image feathering is also tested using real images. In order to overcome the time consuming disadvantage of iterative algorithm for computation of region depth, a fast algorithm is also proposed and tested using convex, concave and cross polygon region. The experiment shows that the method proposed above is very effective and can acquire good results in image feathering of the region.关键词：Polygon region;The computation of depth value;Image feathering2085|137|0更新时间：2024-05-08
- 摘要：Since the traditional H.261/3 and MPEG-1/2 standards employ the block-based compression algorithm, decoded images are suffered from severely blocky artifacts and mosquito effects at low bit rate. To overcome these weakness, object-based video coding approaches are proposed which segment each image into regions of coherent motion.However,the estimation of more complex motion model is required a lot of times and a large amount of computations is,therefore, unavoided.In this paper, a fast temporal-spatio segmentation algorithm is presented using quadric spatial transfirmations motion model.Based on the image spatial segmentation and the estimation of the parameters of quadric spatial transformations motion model, the amount of computation for temporal-spatio segmentation is efficiently decreased through the linearization the estimating for model parameters、Householder transformation and the fast approach forR、zmatrix.关键词：Image coding;Temporal-spatio segmentation;fast algorithm;Quadric spatial transform;Orthogonaltransform2523|129|0更新时间：2024-05-08
- 摘要：As the base of tissues' segmentation, measurement and analysis in angiographic images, edge-detection is one of the emphases in research for the angiographic image's characteristics of low signal-to-noise ratio,plentiful low-level textures, and gently ramped edges. Edge-detection is the base of tissues' segmentation, measurement and analysis in angiographic images.In general, digital angiographic image's signal-to-noise ratio is low, and there are plenty of low-level textures. Moreover, almost all of the edges are ramp and weak ones. The edge-detection is still one of the emphases for research and clinical applications. This paper presents a new method for detection of the edges in digital angiographic images. We found that histograms of local regions across edges of images are statistically different from that of those where no edge is crossed. This difference can be utilized for the detection of edges of angiographic images. We propose a maximum statistical relativity (MSR) algorithm that is a kind of matching filter. As a result, the edge-detection algorithm is not sensitive to noise and low-level textures of images.关键词：edge detection;histogram;Segmentation;Maximum statistical relativity (MSR) algorithm1904|118|0更新时间：2024-05-08
- 摘要：Image registration is a fundamental object recognition method in computer vision. It aims to find a best match of an object image in an image to be processed. In this paper, we concentrate on image registration from image feature point-sets. A new method is proposed which is based on the conventional correlation measure of two point-sets which was introduced by Umeyama. The traditional Procrustes analysis method is used to normalize the point-sets. The novelty of the proposed method is by introducing a weight matrix into Umeyama' s correlation measure the limitation of the traditional method, which requires the dimensions of both point-sets to be the same, is released. The proposed method can register two point-sets with geometrical distortion and different dimensions. Point-sets registration results are given in the paper. When the dimensions of both point-sets are the same, both of the proposed method and the traditional method work well. But when the dimensions are different, only the proposed method can register point-sets precisely.关键词：Image registration;Procrustes normalization;Correlation;iterative algorithm2189|143|0更新时间：2024-05-08
- 摘要：The paper presents a new analysis method for effectively recognizing story structures of video programs. First, video stream are decomposed into sequences of video pages, and key frames are also extracted to represent video pages. Techniques and formulations are then proposed to match and cluster video pages of similar visual contents, taking into account the visual features and temporal arrangement of clustering elements. In addition, we use the Sequence Structure Graph representation to show the story development clue—story line extracted from video. The proposed analyses lead to automatic segmentation of story units and the building of a compact representation of video contents. Hence we are able to decompose video into compact representations that reflect the flow of stories. This offers an efficient mean for browsing and non-linear access of video. Experimental results demonstrate the effectiveness of the new analysis method.关键词：Video page;Video stream decomposing;clustering analysis;Sequence structure graph2234|125|0更新时间：2024-05-08
- 摘要：Triangulation from 3D points set is one of often using ways in which 3D surface is restored. But in practice, it needs to process a huge of data, so it is time consuming. Based on the fact in 3D restoration that most sequential section contours of an object are similar to adjacent ones, a quick method on triangulation between two section contours is proposed in this paper. First, the dominant points of every contour are located, then the dominant points of two contours are matched each other, so the area between two contours is segmented into multi smaller areas. And then triangulation is performed in each small area. Because of the pre-matched dominant points, a simple and quick triangulation can be applied. In this paper, the strategy of triangulation we used is:keep the proportion of the numbers of the dots not used on two curves in accordance with that of whole numbers of the dots on the two curves. Analysis by theory and experiments show that the visual effect of this algorithm is almost the same in computing with common global optimizing methods, and it spends much less time. So the algorithm is effective.关键词：Dominant point;Triangulation of 3D surface of object;Cross-section contour;match2232|120|0更新时间：2024-05-08
- 摘要：Face recognition technology (FRT) has numerous commercial and law enforcement applications, especially in video surveillance. The primary task at hand, given still or video images, requires the identification of one or more persons using a database of stored face images. Based on Fisher discriminant criterion, In order to extract features by using the uncorrelated discriminant transformation, we use orthogonal wavelet transformation and KL transformation to process the face images at first. According to peoples' recognition experience, we use multi-feature and multi-classifier combination to give out the classification results. Experiments on ORL database obtained an error rate of 2%, which is the best result on this database up to now. Experimental results also show that this method does not sensitive to the pose and expression of human faces.关键词：face recognition;Optimal discriminant transformation;wavelet transformation;KL transformation;Combining classifier1946|145|0更新时间：2024-05-08
- 摘要：Model-based facial image coding has received extensive attention due to its high subjective image quality and low bit-rates. But the estimation of object motion parameters is still a difficult problem. In this paper, head motion characteristics is analyzed, and it can be classified into three motion types, head rigid motion, simple motion of facial expression and complex motion of facial expression. A motion parameter estimation algorithm based on corresponding feature points is utilized to extract head rigid motion. A linear implementation algorithm is suggested. The key works to improve the accuracy of motion parameter estimation are the selecting of some proper feature points and the building of an exactly 3D wire-frame corresponding to specified face. A deformable matrix is constructed to extract simple motion parameter of facial expression. At last, the error of motion parameter is evaluated by the area-error function.关键词：Model-based coding;Image analysis;Image synthesis;3D wire-frame model;Motion parameterestimation2386|145|0更新时间：2024-05-08
- 摘要：Color is one of the most significant inspection criteria related to apple external quality. In this paper, a computer vision experimental system for apple color estimation was first discribed. The system included a single-lane conveyer, an apple illumination chamber, and the hardware fot apple image acuquisition and procession. A method of using HSI color system and neural network techniques for apple color inspection was developed. A GA-based training algorithm was introduced to find optimal structure or the number of hidden layer nodes and connection weghts of artificial neural network. The results of experiment show that the approach is effective fot real-time color grading and is accurate. The vision system achieved over 90% accuracy in color classification for apples by representing features with hue histograms and applying artificial neural network. The executing time of microcomputer for grading of one apple is 150ms.2748|160|0更新时间：2024-05-08
- 摘要：Physical characteristic of Chinese-medicine tongue is mainly reflected by colors, in the research of tongue analysis instrument, the most important and hard technique is how the colors to be measured and how to keep the accordance and repeated of colors between the different devices. In this paper, the structure of tongue analysis instrument is briefly described. Choice and design of illumination is given, and the color calibration method to camera and CRT using artificial neural network is presented.关键词：Tongue analysis instrument;Color calibration;Illumination;color space;neural network2462|141|0更新时间：2024-05-08
- 摘要：The growth of osteoma is soakage.Osteoma' boundary organ reflect the biological behavior of osteoma. Therefore,it's important to study the fractal characteristics of osteoma boundary.However,there was lack of quantitative parameters depicting these characteristics in the past.With regard to the osteoma of soakage growth, the prognosis is different because of various degree of soakage.It is necessary to use the characteristic parameter in order to reflect soakage growth degree of osteoma. Thus, the fractal characteristics of osteoma boundary is discussed in this paper. Our results show that fractal dimension can preferably reflect the soakage growth of osteoma' boundary organ. It is a robust characteristic parameter in describing different pathological changes degree of osteoma and prognosis. This provides a new useful approach for lucubrate of osteoma.关键词：fractal;mathematical morphology;osteoma boundary2483|205|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