最新刊期
卷 12 ， 期 6 ， 2007
- 摘要：This paper is the twelfth of the literature bibliography on computer graphics engineering in China in 2006. We collected and classified most of important papers in computer graphics field published in Chinese, selecting references from 11 important Chinese journals published in 2006 and classified these references into different categories according to their contents. Based on the overview and analysis work, we found that the number of researchers and developers engaged in computer graphics-related field is increasing a lot in the past 10 years, and many conferences are held each year, many high-level achievements are made in China. In addition, computer graphics develops itself, deriving out some new research topics or directions even cross disciplies.关键词：graphics engineering;graphics processing;computer graphics;survey2555|220|0更新时间：2024-05-07
- 摘要：The algorithms based on wavelet transform have been very popular in image processing applications such as image compression, denoising, segmentation, texture analysis and synthesis. Multiscale statistical models for image characteristic are the key problems for these applications. This paper reviewed the statistical models for images in wavelet domain. Firstly, the marginal models for non-Gaussian distribution of image wavelet coefficients were studied, then the dependency models including interscale, intrascale and composite dependencies were analyzed, and the paper indicated the advantages and disadvantages of the models and gave normalized measures for the abilities of different dependency models to capture the dependencies between coefficients. At last, image statistical models based on multiscale geometric analysis were introduced in brief, and the possible future work is pointed out.关键词：wavelet;multiscale statistical model;non-Gaussian;dependency model;mutual information;multiscale geometric analysis3419|218|0更新时间：2024-05-07
- 关键词：vector median filters;spatial distance weighting;impulsive noise;color images;adaptive techniques3018|203|0更新时间：2024-05-07
- 摘要：An image denoising scheme based on wavelet packet and level dependent adaptive threshold is proposed in this paper. By using wavelet packet, the scheme not only decomposes the image into the low frequency part but also into the high frequency part of image so that the influence of noise can be eliminated. Meanwhile, using the level dependent adaptive threshold to process wavelet packet tree coefficient with soft threshold can keep edge information and important image information better since the soft threshold can clearly make the SNR of denoised image higher than general threshold. From the experiment results, we see that such scheme can not only suppress additive Gaussian white noise but also well keep original image information. The proposed method is useful for advanced image processing.关键词：image denoising;wavelet packet;adaptive threshold3260|229|0更新时间：2024-05-07
- 摘要：EO-1 Hyperion sensor is the first spaceborne hyperspectral instrument to acquire both VNIR and SWIR spectra. A Hyperion image which covers the middle part of the southeastern Chocolate Mountains district and the Rainbow mine area was used to evaluate the utility of Hyperion imagery in identifying gold-related rock units in this area. A group of pre-Tertiary gneiss appears to be the favorable host of gold deposits in the district. Satellite mapping of gold-associated lithologic units is helpful for the search for gold and understanding the regional geology. Pre-processing aspects of Hyperion data before it can be used for information extraction were first addressed in the study. The data dimension was reduced for data redundancy removal and feature extraction. A supervised classifier was finally used to extract the lithologic units that are significant for gold exploration in the study area. The result shows that MLC classifier is efficient for the extraction of lithologic units from the Hyperion data in the study area, and the resultant rock units have excellent correlation with those on the geologic reference map. The MLC classifier creates a "hard" classification with an overall accuracy of 86% and a Kappa coefficient 0.81. This case study indicates that Hyperion data can achieve accurate mapping of gold-associated rock units in the southeastern Chocolate Mountains.4657|274|0更新时间：2024-05-07
- 摘要：In this paper, an ISS algorithm with adaptive parameters has been proposed. It takes into account the features of human visual system(HVS) and thus can limit the local distortion of the watermarked images. By doing this way, the watermarking scheme has better transparency and stronger robustness. Experimental results demonstrate that the proposed algorithm overcomes big local distortion existed in ISS scheme, and is robust enough against many kinds of image processing such as JPEG compression, noise filtering.关键词：digital watermarking;improved spread spectrum;HVS2897|222|0更新时间：2024-05-07
- 摘要：By unifying the cross-entropy and the image optimal block processing, a digital image scrambling degree evaluation method based on block cross-entropy is proposed. To reflect the image scrambling effect by image cross-entropy, the scramble transformations with periods are simulated. The results show that: the proposed method is effective to describe the relationship between the enciphering effect and the number of iterations in the enciphering techniques, which largely consists with human vision. For different images, when some transformation is used, this appraisal method can reflect to some extent the scrambling effects in each encryption stage.关键词：digital image;scramble transformation;cross-entropy;image scrambling degree4032|266|0更新时间：2024-05-07
- 摘要：The traditional image quality evaluation metric, such as PSNR, cannot reflect the visual perception to the image effectively. Concerming this issue a content-based image quality assessment metric is proposed in this paper. Based on a structural-similarity-based metric(SSIM) with some modifications, our approach partitions an image into three parts: edges, textures and flat regions according the content of the image and then we apply the SSIMs to fuse each part using Sugeno fuzzy integral. The new metric combines the position and quantity information with the similarity of the image structural information and gives comprehensive evaluation to the quality of the specified image. The experiment results illustrate that the proposed metric has good correlation to the subjective perception, and can reflect the image quality effectively.关键词：image quality assessment;structural information;distorted image;fuzzy integral3307|240|0更新时间：2024-05-07
- 摘要：This paper presents a new method for objective measurement of out-of-focus blurred images of one authentic image. The essential idea is to derive the point spread function(PSF) of an out-of-focus blur image from the line spread function(LSF). In this method, it is assumed that at least one sharp edge could be detected. The LSF is thercafter constructed from the edge(s). This approach has fast speed as it works in spatial domain with neither complex Fourier transform nor iterative computation. Moreover, a generic criterion for out-of-focus blur measurement is proposed and it can be applied to all images being independent of image contents. The experimental results validate the accuracy and efficiency of the proposed method.关键词：out-of-focus;point spread function;lines spread function;blur measurement;edge detection3912|213|0更新时间：2024-05-07
- 关键词：image processing;FFT;precision analysis3110|235|0更新时间：2024-05-07
- 摘要：Video object extraction has been a most discussed topic in the field of modern information processing. In order to improve the performance of the common temporal-spatial segmenting algorithms and to obtain video objects with ideal boundaries, a novel video object spatial watershed segmenting strategy is proposed in this paper. This strategy combines the merits of alternating sequential filtering by reconstruction and adaptive threshold. The reduction of the number of the segmented regions without complicated area merging is guaranteed by the iteration of morphological filtering of opening and closing by reconstruction with gradually expanding structural elements. Besides, the iteration makes it easier to distinguish the gradient of the object boundary pixels and that of the pixels inside the foreground and background plateaus. This process facilitates the application of the adaptive threshold algorithms to remove the small regions of local gradient extreme. Several comparative temporal-spatial segmenting experiments have been implemented on some standard testing sequences. The experimental results indicate that the proposed strategy has achieved satisfactory spatial segmentation and enhanced the performance of the temporal-spatial segmenting algorithm for the subject and the object. Additionally, appropriate structural element size of the morphological filter and the non-linear threshold values can be automatically generated. This ensures fairly good versatility and usability of the algorithm.关键词：video object extraction;watershed segmentation;alternating sequential filtering by reconstruction;adaptive threshold3027|221|0更新时间：2024-05-07
- 摘要：This paper suggests an improved marker-based watershed image-segmentation method to reduce the over-segmentation of the watershed algorithm. The new method applies the watershed transform directly on the original gradients image instead of simplified image, so that the loss of boundary information can be avoided. On the other hand, we design a new marker-extracted approach to extract the regional minima related to the objects from the low frequency components of the gradients. These extracted minima constitute the binary marker image. And then the extracted markers are imposed on the original gradients as its minima, while all its intrinsic minima are suppressed. Finally, the watershed algorithm is applied to the modified gradients by the markers to reduce effectively the over-segmentation. Across a variety of image types, it is proven that this new method can obtain meaningful and homogeneous regions with accurate, consecutive and one-pixel wide boundary. Compared with other methods, this system requires fewer computations and simpler parameters and can more efficiently reduce the over-segmentation of the watershed algorithm.关键词：imgae segmentation;color image gradients;Butterworth filter;mathematical morphology;marker extraction;watershed7176|319|0更新时间：2024-05-07
- 摘要：Difficulties in obtaining satisfied sample data of remote sensing image and the lack of effective methods to accumulate and manage them are the bottlenecks for the development of classification technology. Against these problems, a CBR(case based reasoning) system for remote sensing classification is established on the base of modified Fuzzy ARTMAP neural network in this paper. In the CBR system, the modified Fuzzy ARTMAP neural network plays the roles of the knowledge extractor of cases and the classifier of remote sensing images. Reasonable reserve, optimization combination and reutilization of remote sensing samples can be implemented with the CBR strategy. The TM image of Xiang Hai nature reserve is classified by following four methods respectively: the CBR system, maximum likelihood, BPNN and modified Fuzzy ARTMAP. Experimental results show that, comparing with other classification methods, both the utilization efficiency of remote sensing samples and the classification accuracy of images can be greatly improved by the CBR system. The problem of how to utilize the existing samples efficiently for remote sensing classification when the sample data of the current image are limited can be solved to a certain extent in the proposed system.关键词：case based reasoning;remote sensing;classification;sample reuse3305|219|0更新时间：2024-05-07
- 摘要：With the development of aerial photogrammetric technology and the digital camera’s spatial resolution. It is possible to use photogrammetric technology in the inspection of power lines. However, there is little published method for automatic extraction of power lines from aerial images. In this paper, an algorithm of automatic extraction of 550kV power lines from complex background in aerial images is presented. Linear feature operators are designed to resist the strong noise and the potential power line pixels are acquired by Ratio operator. PartRadon transform is used to acquire and link the segments. The gaps of the power line segments are filled through similar Kalman filter tracing method. The proposed method is validated by the experimental images.关键词：power lines;aerial image;linear feature operator;RADON transform;Kalman filter3194|202|0更新时间：2024-05-07
- 摘要：Intravascular ultrasound(IVUS) can provide clear real-time cross-sectional images with lumen and plaque. Affected by pulse, the collected sequential images of the coronary artery, will be overlapped and distorted. As a result, the relativity between image sequences is destroyed. And the veracity of border detection of quantificational measurements and of reconstruction can not be achieved. In this paper, a new phasic registration technique without hard ware is used to resample the sequential images at the same phase. Then those resampled images are traced by a improved border detection technique based on fast active contour model. The experimental result shows significant accordance between the automatically detected luminal and vessel areas and the manual tracings with high correlation coefficients and small system error and the method can be a reliable and accurately way of diagnostis.关键词：intravascular ultrasound;biplane angiogram;active contour;border detection;luminal border;medial-adventitial border3060|209|0更新时间：2024-05-07
- 摘要：The automatic recognition by gait has recently gained more and more interests as the unique performance to recognition people at distance. An appearance-based approach to improve the gait recognition is proposed. The vector data scanned from horizontal, vertical and diagonal direction of the outer contour of binarized silhouette of a walking person are chosen as the image feature. These temporal and spatial feature sequences are decomposed based on the discrete wavelet transformation(DWT) to reduce data dimensionality and filter the noise produced from the procedure of template extracting. Then the multi-class support vector machine(SVM) models are trained by the decomposed feature vectors. The gaits are classified by the trained SVM models. This algorithm is applied to a data-set including thirty individuals. Extensive experimental results demonstrate that the proposed algorithm performs at an encouraging recognition rate with 91% at relatively lower computational cost.关键词：biometrics;gait-based recognition;silhouette projection;discrete wavelet transformation(DWT);support vector machine(SVM)2938|211|0更新时间：2024-05-07
- 摘要：In the paper, based on geometry theory, a new fast iterative algorithm for support vector machine(SVM) classifier design is presented. It is known that the optimal hyper-plane of SVM is completely constructed using its support vectors. Once all support vectors of two classes are identified, the optimal hyper-plane can be determined. Based on geometric distribution of the trained sample points, the new algorithm establishes an initial candidate support vectors set by locating the two closest points of the two opposite class. The new algorithm starts from two closest points of the opposite classes to seek the support vectors accumulatively. The new algorithm continually seeks the points which are the violators of KKT condition as support vectors. At last, the new algorithm acquires all support vectors and establishes an optimal hyper-plane. To validate the new algorithm, some experiments which compare the new algorithm with the SMO algorithm and DIRECTSVM algorithm are performed. The experimental results have shown the generalization ability of the new algorithm is the same as that of SMO algorithm and DIRECTSVM algorithm. The speed of the new algorithm is superior to the other two algorithms.关键词：geometric algorithm;support vector;support vector machine(SVM);classification2961|204|0更新时间：2024-05-07
- 摘要：Mutual information registration based on pixel intensity has been widely used in recent years. However, its application to subimages with small samples is questionable, because many localmaximums may happen or the global maximum may be away from the actualmaximum value which causes unnecessary registration error. A new approach, mutual information registration based on feature label(MIF), is proposed to solve such problem. This method first uses image’s intensity and gradient features to train the selforganized mapping(SOM) neural network, and then builds up the feature classifier for each modal image. Using such a classifier, images are project into a feature space with decreased dimensions. Finallymutual information is evaluated in the feature space tomatch images. Our results demonstrate that this method increases the success rate of the subimage registration, and is optimal for thewhole images(eitherwith or without noise) elastic registration.关键词：image registration;elastic registration;mutual information(MI);feature classify;feature label3260|220|0更新时间：2024-05-07
- 摘要：Elastic registration is a difficult problem in image registration technology. An elastic point registration method using the Hausdorff distance is presented in this paper. With B-splines as the deformation model, the proposed method is able to handle elastic deformations between the images to be registered. Since no correspondence is required to be established between two point sets, the method is robust to outliers. In addition, a sequential updating strategy is introduced to further speed up the elastic registration method by dividing the source image and the grid of control points into separate blocks. The performance of the proposed method is demonstrated and validated in three experiments, a synthetic image registration experiment, a hand-drawn character registration experiment, and a brain MRI image registration experiment. While these results are somewhat preliminary, they clearly demonstrate the applicability of our method to real world tasks involving feature-based elastic registration.关键词：feature-based registration;elastic registration;the Hausdorff distance;outlier rejection;B-splines3884|205|0更新时间：2024-05-07
- 摘要：Zernike moments are used as a shape descriptor for complex shapes that are difficult to be defined with a single contour such as trademarks. The Zernike moments of a given shape are calculated as correlation values of the shape with Zernike basis functions in that all the pixels of the shape regardless of their positions contribute with the same weight to the Zernike moments. The proposed modified Zernike Moment descriptor is obtained by the following two steps: firstly divide the original shape into three parts of inner, middle and outer regions with tow predetermined radius, then calculate the Zernike moment of each part reseparateively. The modified descriptor takes account of the partition radius of the shape according to human perception, meanwhile, using relevance feedback technology to fix the importance of the each part as mentioned above could improve the efficiency of retrieval process. Euclidean distance is used to compute the distance between two shapes. Experimentation under various test conditions shows the effectiveness of the proposed modified method.关键词：image retrieval;shape representation;Zernike moment;weight;relevance feedback3198|202|0更新时间：2024-05-07
- 关键词：grid sampling;range image segmentation;feature extraction;principal component analysis3391|235|0更新时间：2024-05-07
- 摘要：The kernel of a plane simple polygon is a point set in the interior of this polygon, in which any point can be connected to another arbitrary point on the border of the polygon with a line inside the polygon. The character of kernel finds its application in such fields as the positioning of the camera. We propose a new method to calculate the kernel of a single polygon, which can not only judge the existence of the kernel, but also get the point list of the kernel. The given arithmetic is easy to understand and realize, and can be widely applied to such kind of problems.关键词：simple polygon;kernel;computational geometry2484|179|0更新时间：2024-05-07
- 摘要：This paper analyzes the character of the complex canal network, and imports the dynamic segmentation theory to organize the canal network data and its spatial knowledge. A method based on grid to detect the network density is put forward and the result show it is better than other method. And also a canal network selection model is set up based on decision of spatial knowledge. This model integrates five factors of the canal selection such as the attribute, length, link condition, spatial relation between canals and network density. Then, utilizes the multiple criteria decision to evaluate each canal by these five factors, and make alternated selection to preserve the whole network character关键词：automated map generalization;spatial relationship;multiple criteria decision model;dynamic Segmentation2637|181|0更新时间：2024-05-07
- 摘要：On the basis of analyzing existing commonly used interpolation methods for generating the regular grid model from the corresponding contour line model, this paper presents a new interpolation method based on block and point-by-point interpolation technology. This algorithm has already been accomplished with Microsoft Visual C .net programming. And the result of interpolation has been successfully applied to the Terrain Visualization Platform.关键词：digital elevation model;interpolation;terrain visualization2872|164|0更新时间：2024-05-07
- 摘要：By Bring in integral principle and the idea of Kruskal/2-opt algorism, a new tour construction algorism with time complicity O(N2) is presented in this paper. In fact, carving path of laser carving machine could be transferred to the traveling salesman problem(TSP) and optimized for laser carving process(LCP). In this algorism, some reasonable small loops are constructed in the first step, then larger loops are progressively synthesized with the small ones from bottom to top and in the end, a near-optimal resolution can be captured in this way. Moving distance resulted from this calculation is about 1.1 times of lower bound due to Held and Karp. Experimental results show that in the case of laser engraving machine, this algorism can reduce the vacancy path by 88%.关键词：laser engraving;TSP(Traveling salesman problem);tour construction algorism;global construction principle3178|188|0更新时间：2024-05-07
- 关键词：autostereoscopic display;parallax;horizontal position disparity;stereoscopic vision2890|189|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