最新刊期
卷 11 ， 期 5 ， 2006
- 摘要：This is the eleventh in the survey series of the yearly bibliographies on image engineering in China.The purpose of this survey work is mainly to capture the up-to-date development of image engineering in China,to provide a convenient means of literature searching facility for readers working in related areas,and to supply a useful reference for the editors of journals and potential authors of papers.Considering the wide distribution of related publications in China,656 image engineering research and technique references are selected carefully from 2 734 research papers published in 112 issues of a set of 15 Chinese journals.These 15 journals are considered as important journals in which papers concerning image engineering have higher quality and are relatively concentrated.Those selected references are classified first into 5 categories(image processing,image analysis,image understanding,technique application and survey),and then into 23 specialized classes according to their main contents(Considering the progress of image engineering,2 new classes for focal topics are added this year).Some analysis and discussions about the statistics made on the classification results are also presented.This work shows a general and off-the-shelf picture of the various progresses of image engineering in China.It should be pointed out particularly that,in 2005 the number of research papers for image engineering,published in the above 15 journals attends a new stage in the history.A tendency of continuing development of image engineering in China is clearly visible.关键词：image engineering;image processing;image analysis;image understanding;technique application;survey;statistics;classification3636|242|0更新时间：2024-05-07
- 摘要：This paper proposes a new recognition algorithm based on fractal dimension and image center of gravity after the segmentation of marrow cell images in the clinical haematology and cytology atlas which can be used to extract. The fractal feature of every marrow cell image. Since the texture of a color image contains not only certain statistical similarity but also the color distributions, a new color parameter is extracted from the color images of marrow cells and discussed with parameter S of HIS for the fractal dimension. The experimental result shows that different marrow cell image has the certain discrimination in fractal dimension and some images can be recognized for classification.关键词：marrow cell;fractal;differential box counting;color parameter2922|218|0更新时间：2024-05-07
- 摘要：This study applies graph spectra and probabilistic neural networks to the task of supervised images classification. At first, comers are extracted from images to construct Delaunay graphs. These relational graphs have proved alluring as structural representations for images. Then graph spectral decomposition method is adopted to get eigenvalues and eigenvectors of the adjacency matrix. Graph spectra can preserve the primary structure of graphs. The spectrum of these graphs will be used as feature vectors for classification. At last probabilistic neural networks will give the classification result according to the vectors . As for the classifier, PNN has high speed of learning because the learning rule is simple and new trainings patterns can be incorporated into a previously trained classifier quite easily, which might be important for a particular on-fine application. Experimental results show that this method can achieve the best result of images classification.关键词：graph spectra;images classification;probabilistic neural networks3035|207|0更新时间：2024-05-07
- 摘要：A multi-scale morphological algorithm for color images segmentation is proposed in this paper.At first,color watershed transform is applied based on tensor gradient to get initial segmentation,i.e.local level connected sets.Both area and color are considered to calculate the similarity between adjacent regions.Then,a RAG(Region Adjacency Graph) and a NNG(Nearest Neighbor Graph) are constructed to accelerate following morphological processing.Finally,color morphological operators are defined based on a special full order relation of color vectors in HSV model.Morphological opening-closing is implemented using vertex-collapse algorithm.A nonlinear scale space will be constructed efficiently with perfect shape preserving.Since extrema in an image are always associated with objects,particular objects are extracted at different scales.Entropy criterion is adopted to control the content contained in the final scale tree.关键词：segmentation;color image;morphology;nonlinear scale space;and vertex collapse2822|204|0更新时间：2024-05-07
- 摘要：Automatic identification of structural characteristics is an important research area for computer aided design of woven fabric.Since the skew is inevitable during fabric scanning,a fast skew detection algorithm based on Hough transform for the fabric surface image is proposed.In order to reduce compute complexity,the information of weft direction is extracted from the gradient of fabric image firstly.Then,hierarchical Hough transform is used to estimate the skew angle of fabric image with satisfactory precision.Finally,based upon the skew detection process,a novel algorithm to identifying the weft density is introduced,which is independent of the image skew.The projection profile on skew angle is used to determine the arrangement of weft yarns,and the density of weft is easily computed.The experimental results show the practicability and efficiency of our method.关键词：skew detection;Hough transform;weave pattern;weft density3082|213|0更新时间：2024-05-07
- 摘要：In this paper,we propose an automatic multispectral remote sensing image classification technique based on improved probabilistic diffusion.Firstly,the optimal number of clusters in multispectral images is determined by comparing the validity functions of fuzzy c-means classifier(FCM).The posterior probability maps for each class are then smoothed by an improved version of multispectral anisotropic diffusion based on morphology.Finally,each pixel is classified independently using the maximum a posterior probability(MAP) estimate based on probabilistic membership maps.Because of the elegant property of anisotropic diffusion,edge-preserving smoothing,probabilistic diffusion,not only restrains effectively speckles in homogeneous regions,but also preserves preferably the significant physiognomy and edge features.Experimental results are given to show that the proposed method avoids the influence of "class noise" and its overall accuracy and Kappa coefficient have superiority capability over the traditional maximum a posterior probability estimate classification method without probabilistic diffusion.Thus it is an ideal remote sensing classification method.关键词：anisotropic diffusion;probabilistic diffusion;muhispectral remote sensing image classification;maximum a posteriori probability;diffusion coefficient2704|211|0更新时间：2024-05-07
- 摘要：To solve the problem of false positive in micro-calcification detection,a two-layer support vector classifier model with rejection feature(TLSVCRF) is proposed.Firstly the first layer of support vector classifier(SVC) with maximum margin between two classes will be used for classifying the input pattern;then the sphere support vectors of true micro-calcification points to describe the distribution of the sample were obtained by searching all the sphere boundaries containing the samples of this class.Then the input pattern of no-object classes could be rejected by the second support vector domain description(SVDD).Lastly the results of SVC and SVDD classifier are integrated to obtain the right results.Experimental results demonstrate that the method of two-Layer support vector classifier with rejection feature performs better in achieving lower false positive.关键词：support vector classifier(SVC);micro-calcification detection;support vector data description(SVDD);rejection performance2829|185|0更新时间：2024-05-07
- 摘要：X-corner patterns are most widely used in camera calibration. In order to do online calibration for blurred image,we propose a new algorithm for X-corner detection based on the special character of X-corners: the pattern is symmetrical and the gray contrast greaty with each other In the algorithm the operator SV is designed to recognize X-corners which consists of symmetry operator S and variance operator V.The method is smart,easy to execute and robust to rotation,intensity change.It is also robust to image noise and edge blur where the intervention of man is not required.Experimental results show that the proposed algorithm can achieve excellent effects in X-corners detecting.in on line camera calibration.关键词：X-corners;corner detecting;edge blur;camera calibration;Harris detector5526|219|0更新时间：2024-05-07
- 摘要：This paper proposes a Geometric Feature Map method bused on multi-viewpoint range images. After every range image of 3D model is phase encoded, a histogram about the planar surface normal and size of 3D model can be worked out. By using principal component analysis, we can obtain a series of range images and the corresponding histogram of 3D model based on the best viewpoint range image. Similarity measurement between two models can be obtained by calculating the distance of the corresponding histograms of two models. The experimental result shows that our method is invariant to the translation, the rotation and the scaling of 3D model and is robust to the simplification of 3D model, and suitable for the classification of 3D model.关键词：3D model retrieval;geometric feature map(GFM);range image;phase encoded Fourier transform2504|223|0更新时间：2024-05-07
- 摘要：In order to obtain an interpolated image with a superior quality, this paper presents an efficient image interpolation technique using many-knot spline basis function with compact support. The one-dimensional many-knot splines interpolation algorithm is extended to that of two dimensions, which is applied to image processing. Then the accuracy of approximation, regularity of many-knot splines interpolation method and frequency property of the interpolation kernel are worked out for comparison. It can be shown that the approach is superior to other methods, such as cubic convolution. The experimental results proved that the algorithm can produc reconstructed images of superior quality.关键词：image interpolation;many-knot splines;approximation order;regularity;peak signal noise ratio(PSNR)2704|206|0更新时间：2024-05-07
- 摘要：An improved adaptive median-based filter,based on extremum median filter,is proposed to restore images corrupted by salt and pepper noise,especially for those with unknown noise ratio.There are mainly two improved points in this algorithm:(1) a fuzzy measure is proposed to judge the noise ratio;(2)a gradient operator is introduced to save the thin lines,such as edge information.It gets some useful information by training and simulating.Compared with traditional median filter,ordering threshold switching median filter and improved median filter proposed by Sorin Zoican,our approach is more adaptive and receives better results.关键词：fuzzy measure;median filter;impulse noise;gradient operator3427|213|0更新时间：2024-05-07
- 摘要：This paper presents a computer model capable of generating cartoon puff and dust. We first classify existing cartoon puff and dust into different types according to their forms and dynamics, then construct skeletons defining their static and dynamic structures in 3D space. Based on those skeletons, final forms depicting relevant puff and dust are added to skeletons. The advantage of our model over the hand-drawn cartoon puffs and dust is generating cartoon puffs and dust with perspective under different view points which can effectively avoid reoetitive work of the animator when drawing corresponding effects.关键词：puff and dust;model;cartoon animation;computer animation2958|205|0更新时间：2024-05-07
- 摘要：A panorama rendering algorithm of video sequence based on homography transformation between frames is presented in this paper. Firstly, the hierarchical model-based motion estimation is adopted to compute the adjacent homography matrix. Then, for non-adjacent frames, the homography matrix is estimated by guided feature registration based on RANSAC algorithm, which can obtain sub-pixel accuracy. Finally, the video sequence panorama is rendered using temporal median filter.关键词：video processing;panorama;homography transformation;RANSAC;hierarchical estimation2765|185|0更新时间：2024-05-07
- 摘要：Traditional fractal pattern design has some disadvantages such as being lack of the ability for describing basic cell of pattern and unable to effectively reflect the characters of real scenery. In order to solve the problems, we present a novel pattern design technology of fractal geometry based on image texture rendering. First we improve the texture synthesis algorithm of Wei by using two-dimensional autocorrelation function to analyze the structure and distribution of the texture first, and then determine the size of L neighborhood. Second several special fractal sets are adopted and HSL color space is chosen, so that the fractal structure can be used to manipulate the texture synthesis. The experiments have shown that using the novel technology patterns with different style, color, texture characteristic can be generated quickly.关键词：fractal geometry;texture synthesis;two-dimensional autocorrelation function;pattern design;image render2595|197|0更新时间：2024-05-07
- 摘要：While implicit surface or surface deformation is represented by multiple metaballs, bulge, crease and tearing frequently appear in overlap area. Researchers tried to tackle the defect by means of adjusting parameters of metaball, simple superposition and direct union. However, they failed to reach expectant result. By the study on single metaball influence and multiple metaball influence overlap, the authors present several blending methods for point, line segment and curve segment skeleton respectively. The multiple metaball influence overlap blending methods include linear weight blend, algebraic blend, and exponent average blend. These blending methods are independent from the expressions of surfaces and the field function formula of metaball. Case studies show that the effect and efficiency of the suggested methods are satisfied.关键词：metaball;skeleton;blending;bulge;crease3111|169|0更新时间：2024-05-07
- 摘要：Volume rendering method is one of the most typical algorithms of 3D image reconstruction. The two basic operations, resampling and interpolation, are the most time-consuming operations, which usually affect the reconstruction speed. So, some measures and methods of decreasing interpolation, fast interpolation and fast resampling are proposed in paper. The result shows these measures is practical and effective.关键词：3D reconstruction;volume rendering;interpolation;resampling2742|191|0更新时间：2024-05-07
-
Robust Tracking of Objects in Image Sequences Using Multiple Degrees of Freedom Mean Shift Algorithm
摘要：Current Mean Shift tracking algorithm uses a single radius parameter to describe the scale of the target,and Each target has the position and size freeness only,which is not suitable for complex movements of the objects.In this paper we provide a new algorithm in which a bandwidth matrix is employed to describe the objects with two directions determined independently.Target-angle is also introduced to accommodate the rotation of objects.Furthermore we bring forward an efficient search strategy to cope with a temporal occlusion of the objects.Experimental results show that the new algorithm is able to adapt to any kind of object's movements and therefore has better tracking precision.关键词：Mean Shift;tracking of objects in image sequences;target-angle;bandwidth matrix;adaptability2368|214|0更新时间：2024-05-07 - 摘要：To select an appropriate algorithm for DEM matching,this paper reviews the development of the two popular 3D surface matching algorithms,least z-difference(LZD) and iterative closest point(ICP),and describes their common logical framework.Then the two algorithms are evaluated qualitatively through theoretic analysis.Finally,the quantitative comparison is performed by a set of tests.The experimental results show that the computational efficiency of LZD is about 9 times higher than ICP.But its pull-in range is slight smaller,and its iterative convergence rate is about 1 time slower than ICP.However,the closer the two DEM are,the faster LZD converges.Therefore,LZD is more appropriate for DEM matching with small pose different.关键词：Keywords matching without control points;least z-difference algorithm;iterative closest point algorithm;digital elevationmodel3302|211|0更新时间：2024-05-07
- 摘要：In this paper, a chaotic modulation digital image zero-watermarking method is proposed. Select some low frequency wavelet coefficients of original or tested image and compute the character of the selected coefficients to create watermarking. The wavelet coefficients is randomly selected by the chaotic method. The experimental results show that the watermarking method is invisible and robust against some image processing such as median filtering, JPEG compression, additive Gaussian noise, cropping and rotation attacks and so on. This method changes the traditional doings that watermarking is embedded into images, and make the watermarked image distortion-free. If the initial value of chaos is unknown, the characteristic watermarking can not be extracted correctly.关键词：zero-watermarking;discrete wavelet transform(DWT);chaos2832|182|0更新时间：2024-05-07
- 摘要：To achieve the copyright protection of digital image,we present a novel zero-watermarking algorithm based on DT-CWT(dual-tree complex wavelet transform).The algorithm doesn't modify any information of the image,therefore it possesses both the invisibility and robustness,while it can resolve the loss of energy of conventional watermarking algorithms based on redundant transform.Exploiting the idea of real wavelet zerotree structure,we choose the vital-coefficient-trees from the transformed image,then by using PCA(principal component analysis),extract the first principal components,quantize and encode them to construct the zero-watermark signal,which is registered to the center of authentication and is used to identify user's copyright later.Experiments show,that the robustness of the algorithm is very good,and it can resist various attacks such as filtering,noising,lossy compression,etc..关键词：dual-tree complex wavelet transform(DT-CWT);Wavelet Zero-tree;principal component analysis(PCA);zero-watermarking2898|220|0更新时间：2024-05-07
- 摘要：At first an acquisition of the compressed video model is proposed,then the super-resolution problem is for mulated within the Bayesian framework and the MAP(maximum posterior probability) criterion,finally a universal solution of the problem is presented by integrating the CCD(cyclic coordinate decent) with SA(successive approximations).In order to resolve the problem that the original high-resolution's quality-reduce function is always unknown,a new estimation method is introduced based on the EM(expectation-maximization) algorithm.The results of the experiment demonstrate that the algorithm not only outperforms the traditional ones on the aspects of PSNR and restoration vision effect,but also has the characteristic of easy extension.关键词：super-resolution;compressed video;image restoration;Bayesian estimation2642|212|0更新时间：2024-05-07
- 摘要：This paper presents a fragile watermarking scheme based on integral wavelet transform.The proposed method uses the Quadtrees structures received by the wavelet decomposition,statistical information on the nodes and secret key to choose the locations where to embed the watermarks.One bit watermark information will be embedded into the right location.The method has some characteristics:(1) it is adapts to medical images authentication due to the high Signal-to-Noise when the watermark embedded into images;(2) ensures the fragileness of watermark when it combines with the statistical information of wavelet coefficient to choose the locations where to embed the watermark;(3) it has a strong orientation ability for tampering because of the characteristics of wavelet decomposition in the spatial-frequency domain;(4) uses the secret key to protect the proposed method.It can resist the malice attack even if opening the method. The experimental result shows that the proposed method adapts to the medical images authentication,it is less complexity and more practicability.关键词：integral wavelet transform;fragile watermark;quadtrees;secret key;orientation2516|217|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