最新刊期
卷 4 ， 期 5 ， 1999
- 摘要：Based on Genetic Algorithm, an algorithm of 3D objects' surface reconstruction from a group of planar contours representing cross section through is proposed. By use of the basic principles of GA and the triangulation of 3D objects' surface, it can optimizes the triangulation of 3D objects' surface to meet the various needs with multi objective fitness value function. 3D polygon crossover and 3D quadrilateral mutation are introduced.2338|142|0更新时间：2024-05-08
- 摘要：This paper presents a new graph simplification model, the varying triangle filtering model, which not only considers the characteristics of computer cartographic generalization but overcomes the shortage of traditional methods as well. This model is easy to understand and operate. Meanwhile it can be used as a practical method in cartography generalization.2236|217|0更新时间：2024-05-08
- 摘要：By integrating wavelet with neural network, a new adaptive wavelet function neural network is proposed in this paper. The wavelet neural network can be applied in classification of remote sensing image through network learning. Experimental results show that the classification of wavelet neural network is superior to that of the conventional maximum likelihood.2598|147|0更新时间：2024-05-08
- 摘要：Fast searching centroids of 2D arbitrary shape is still a key problem in the fields of pattern recognition and object tracking. This paper presents a new fast algorithm by analyzing the moment method, which is based on the character that the sum of distances between centroid and other points is the minimum. The algorithm gets the centroid position just from edge information. The algorithm is robust and can be used in the systems of autonomous robot locating, navigation, tracking and docking.3077|139|0更新时间：2024-05-08
- 摘要：A new fuzzy ARTMAP neural network with adaptive cluster vigilance parameter is proposed. Each cluster (hyper rectangle) has its own vigilance parameter which is adaptively adjusted during the training procedure. And a new learning law that defines the establishments and expansions for either non overlapped hyper rectangles or non overlapped nested hyper rectangles is proposed. The proposed neural network can obtain high prediction rate, which has resolved not only the problem of memory stability and plasticity but also the problem of non convex input patterns, both of which exist in traditional fuzzy ARTMAP neural networks. The simulations of applying the new net to palm prints recognition demonstrate its good performance.2101|125|0更新时间：2024-05-08
- 摘要：In the computer vision system based on structured light, it's difficult to get good result from area where the surface reflectance is low. This paper studied the relationship between the image in diffrent position in three dimensional laser color scanner. A scheme is presented which fuses the contour and structured light information to acquire depth information in some special reflection areas. Some good results have been obtained.关键词：computer vision;Acquiring depth information;Structured light;Information fusion2283|133|0更新时间：2024-05-08
- 摘要：This paper suggests a texture classification algorithm based on the feature symbol random field (FSRF). FSRF is a 2 D representation of the image's bank information. In FSRF, symbol value of a pixel gives out its structure function in texture region and is more valuable than the gray value for texture classification. Meanwhile, several co occurrence matrix features are driven from the FSRF which are more powerful than energy features. This paper also suggests a Hierarchical scheme which leads to 96% correct ratio in the included experiments, while the gray value based method 67.5% and bank energies based method 75%.2595|173|0更新时间：2024-05-08
- 摘要：We introduce multifractal based texture image analysis method in classification of three kinds of B scan muscular images and compare the result with ordinary fractal way. Multifractal based method takes into account of the system regional expression impact and the different layer characteristic in their formability. So we can focus on the ultimate characteristic from the point of local system. Moreover we can describe the texture structure more efficiently and completely to make the problem clear. The experimental result has approved our thought.2156|128|0更新时间：2024-05-08
- 摘要：In this paper, a vertex removal algorithm based multiple resolution model representation is presented,which effectively utilises the coherence of adjacent levels of detail and only records the differences between these levels,leading to an economical storge mechanism. It can be used for LOD display, incremental transmission over a network and mesh compression.2935|172|0更新时间：2024-05-08
- 摘要：In this paper, a segmentation-based hybrid image coding algorithm is proposed which takes the features of the human vision system (HVS) into account. First, a novel criterion for quadtree-based segmentation using contrast masking is presented. This segmentation criterion performs better than the frequently used criterion, block variance. With this criterion, the original image is segmented into uniform blocks of 32×32, 16×16 and blocks of 8×8 to be classified. Then a two-level classifier, based on contrast masking sensitivity and polynomial approximation error, is further applied to the blocks of 8×8 such that all blocks are classified into a few categories: uniform blocks of different sizes, smooth blocks of 8×8 and non-smooth blocks of 8×8. At last, block mean, polynomial approximation and DCT coding are applied to the blocks accordingly. The experimental results demonstrate that the proposed algorithm performs much better than JPEG.关键词：Image compression;Quadtree;Image segmentation;Contrast masking;Human vision system2144|162|0更新时间：2024-05-08
- 摘要：Fast Detection and Segmentation of Moving Sperm targets was performed based on MAD analysis and adaptive thresholding. Static sperms was discriminated from false target via their differences in shape features so as to build a good foundation for an effective Computer Aided Sperm Analysis system (CASA).关键词：Sperm motion analysis;Moving targets detection;Image segmentation2563|175|0更新时间：2024-05-08
- 摘要：Image enhancement is a common procedure in order to enhance the contrast, sharpen the edge and optimize the visual quality of the input image, so that the resulting processed image is more suitable for a given application. The algorithm proposed in this paper, which is based on the sloped-facet model of Haralick and the contrast enhancement technique of Beghdadi, can enhance image efficiently while reducing noise, and it can preserve the original information of image perfectly.2182|164|0更新时间：2024-05-08
- 摘要：A fractal compression and coding method for image based on vector quantization is presented in this paper. It solves the shortcomings such as slow speed and lower compression ratio existed in traditional methods well. And at the same time it achieves the high quality of restored image as well. The experimental result given at the end of this paper proves that our algorithm is quite effective.2545|133|0更新时间：2024-05-08
- 摘要：It is an efficient way to use octree for 3D reconstruction. In this paper, aiming at the true solid reconsturction of medical images, we propose a fast algorithm for construction octree by slicing images on the basis of analyzing the space layout of medical cross section images and the configuration of octree. Besides this, it is easy to program and carry out.关键词：Slicing images;Octree;Octcode;Node;3D reconstruction2561|120|0更新时间：2024-05-08
- 摘要：This paper describes an algorithm in the view of system identication and optimization about how to proofread a digital map in the form of vectormap. As it needs few sampled points and has high speed and enough precision, it is very practical. Finally it was used in the proofreading of Hefei geographic vectormap and satisfied results have been gotten.2412|193|0更新时间：2024-05-08
- 摘要：This is thefourth in the survey series of yearly bibliographies on image engineering in China.Considering the current status of the researches on image engineering and the applications ofimage techniques as well as the distribution of related publications in China,more than 300 research and technique references are selected from near 1500 research papers published in a set of 15 Chinese journals,in which papers concerning image engineering are relatively concentrated.These references are classified into different categories according to their contents.An analysis and a discussion of thestatistics made on the classification results are also presented.This work shows a general and up-to-date picture of the progresses of image engineering in China,supplies a convenient means of literature searching for readers doing researches and/or applications in this field,and provides auseful reference for the editors of journals and potential authors of papers.3202|163|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