最新刊期
卷 12 ， 期 11 ， 2007
- 摘要：With the increasing maturity of traditional image information processing, from the pointof theories and utilities, it is of great importance for researchers to find new theories and new ideas based technology. First, this paper briefly introduces the research contents, main characteristics and basic theories of grey theory. Then the state-of-artofgrey theory in image engineering is summarized and analyzed in three levels: image processing, image analysis and image understanding. In addition, some research fruits of the authors are reported. Finally, some key issues and perspectives of grey theory in image engineering are pointed out. Research conclusions show that in spite of a new theory in image engineering, grey theory is feasible, efficient and almost covers all the fields of image engineering.关键词：grey theory;image engineering;greymodel(GM);grey relational analysis(GRA)5178|417|0更新时间：2024-05-07
- 关键词：story segmentation;content-based video retrieval;news video;contextual3386|209|0更新时间：2024-05-07
- 摘要：This paper presented a survey on the development of flame simulation in computer animation, with a detail introduction to the classification of the works as well as different kinds of methods employed in the field. The methods applied mainly include the particle system method, the mathematic and physics-based method and the texture based method. Each method had their advantages and shortcomings, application scopes and result characteristics. We analyzed three important techniques briefly, including flames details, the control mechanisms and the simulation speed of results, and also discussed the tendency of this direction.关键词：flame simulation;computer animation;particle system;physics-based method;Lattice-Boltzmann method;texture technique3078|232|0更新时间：2024-05-07
- 摘要：Noise detection-based median filters have been widely adopted to reduce impulse noise in images. However, more pixels were misclassified at the high noise density. The drawback has negative effect on image filtering. In order to overcome the drawback, in this paper, the upper-lower median-type noise detector is proposed. Based on the noise detector, an adaptive median algorithm is presented. Experimental results show that the new algorithm can effectively remove the impulse noise and preserve more details of original images.关键词：noise detection;impulse noise;upper median;lower median;adaptive median filter3034|198|0更新时间：2024-05-07
- 摘要：In this paper, residues matrix is used as the factor of filtering for processing effectively phase image. Two kinds of filters for phase image are modified utilizing residues matrix. Modified filters have different filter intensities for different areas of phase image according to noise condition. Therefore they can realize an adaptive filtering effect and can preserve fine details in the interferogram. We describe the implementation of filters in detail. By using interferograms data generated by ERS-1 repeat-pass, their effectiveness is tested.3469|220|0更新时间：2024-05-07
- 摘要：In this paper a novel large target region image inpainting model which can preserve linear structure and texture information is proposed. The model uses a cross isophotes diffusion equation constrain the inpainting order. The cross isophotes equation diffuses considering the edge extent, so the model has good linear structure preserving property. Diffusion of cross isophotes is morphologically invariant and it can fill the target region of the natural scene very well. The euclidean distance is used as the similarity function, while the partial differential equation constraint which is used to enlarge the effect of pixels in linear structure is employed. To reduce the seams caused by this model, and achieve a seamless image, a total variation interpolation constrained by gradient is used in the inpainted result. At last the similarity function is extended, and the target region can be inpainted to the assigned texture. Both theoretical analysis and experiments have verified the validity of the new model.3095|255|0更新时间：2024-05-07
- 摘要：In order to improve the estimation precision of inverse halftoning values whose halftone patterns don’t appear in image training set, an inverse halftoning method based on look up table(LUT) and Elman recurrent network is proposed. Firstly the preliminary LUT is built from image training set. Then the Elman recurrent network is used to approximate the mapping between halftoning and inverse halftoning. After studying, training and optimizing the structure, layers and nodes of the Elman network are established appropriately. With this network the continuous-tones of nonexistent halftone patterns are estimated. And the complete LUT is generated. Experiments show that the proposed algorithm can generate inverse halftoning images of good in both visual effect and PSNR while having low memory requirement and inexpensive computation than some of existing algorithms.2934|211|0更新时间：2024-05-07
- 摘要：Significant luminance and chrominance discrepancies between the different camera views can often be observed in multiview video sequences. In this paper, a luminance and chrominance correction algorithm based on partially overlapped local histogram matching is proposed. In the histogram matching method, amapping function is established by matching the histogram of the original image to that of the reference image. Then the mapping function is applied to the original image to obtain the corrected image. There are two branches of histogram matching according to the mapping function used: global histogram matching and adaptive localhistogram matching. Global histogram matching uses the same mapping function for the whole image, so its performance is relatively low. Adaptive local histogram matching can calibrate the luminance and chrominance effectively by using the local histogram for each pixe,l but the computational complexity is very high. In the proposed partially overlapped localhistogram matchingmethod, the samemapping function is applied to a block of pixels. A conditional block reduction filter is utilized on the boundaries of all the adjacentblocks to eliminate the blocking effect. The proposed algorithm can be used as a preprocessing tool in the multiview video system. Experiment results show that it can improve the performance of the multiview video encoder.关键词：multiview video;luminance correction;histogram matching4036|268|0更新时间：2024-05-07
- 摘要：In this paper, a new image coding algorithm based on DWT and Coutourlet is proposed. Firstly, the wavelet transform is applied to the original image, and the directional filter banks(DFB) are employed to middle and high frequency subbands; Then, the lowest frequency coefficients are optimized according to the wavelet coefficients statistical properties; Thirdly, the new extended spatial orientation tree are constructed; Finally, the encoding scheme is realized by the idea ofSPIHT. The experimental results show that the presented image compression scheme performs better than thatof the state-of-art image coders(SPIHT, WBCT), especially for low bit-rate and texture image.关键词：image coding;Contourlet;optimizing LL subband;the extended spatial orientation tree3113|230|0更新时间：2024-05-07
- 摘要：Since no well-established methods for objective quality evaluation are available, in this paper, a new efficient and reliable objective video evaluation model is proposed based on fuzzy synthetic judgment. FuzZy control is combined with the objective evaluation. First, the essential idea of the model is described systemically. Then the fuzzy membership functions of all factors affecting the video quality are determined. And the fact weights are also estimated by proximate approach algorithm. This model highlights a comprehensive evaluation by taking into account various properties of the compressed video including video quality, fluency and motion speed, and has exlellent compatibility with other evaluation model or standard. Simulation results demonstrate that the proposed evaluation model outperform some other approaches and achieve more reliability.关键词：objective evaluation;compressed video sequence;fuzzy theory3054|239|0更新时间：2024-05-07
- 关键词：APCBOT;bi-orthogonal transform;identical quantization;compressive ratio2770|221|0更新时间：2024-05-07
- 摘要：The goal of this paper was to investigate the application of the LDPC codes in Digital image watermarking. Based on the analysis of the equivalent channel in the digital watermarking system, a watermarking technique for digital image on the basis of LDPC code is proposed. The algorithm embeds and retrieves the watermark signature into and out of the static image by employing the LDPC code technology and the human visual characteristics. The results demonstrate that the proposed technique has greatly decreased the error code rate of the retrieved watermark and improved the robustness and invisibility.关键词：digital watermark;low density parity check code;DCT3204|221|0更新时间：2024-05-07
- 摘要：A blind watermarking algorithm based on the relationship of coefficients in the Discrete Cosine Transform (DCT) domain is proposed. Firstly, the original image is divided into non-overlapping 8×8-pixels blocks, and each block is independently transformed to frequency domain through 2D-DCT. Secondly, according to the relationship of DC and middle-frequency coefficients, a polarity matrix is obtained; and then compare the polarity matrix with binary watermark image after scrambling. Finally, the middle-frequency coefficients of the original image are modified in terms of the comparation result to get thewatermarked image. The binarywatermark is extracted from the watermarked image without the original image. The experimental results show that the algorithm is invisible and robust against the general image processing methods.关键词：digital watermarking;discrete cosine transform;scrambling;polarity matrix;blind extracting3610|220|0更新时间：2024-05-07
- 关键词：spatial data mining;spatial clustering;density;seeds;non-spatial attributes3027|226|0更新时间：2024-05-07
-
-
- 关键词：well-ordered;nearest neighbor rule;crop rows indentification;machine vision navigation2915|204|0更新时间：2024-05-07
- 摘要：To improve the robustness of the tracker, a novel algorithm, the Diverse AdaBoost SVM Tracking(DABSVT) method, is proposed for target tracking in infrared imagery. The tracker trains one Support Vector Machine(SVM) classifier per frame. All of the classifiers are combined into an ensemble classifier using AdaBoost. By proper parameter adjusting strategies, a set of effective SVM classifiers with moderate accuracy are obtained. The ensemble classifier is used to distinguish the target from the background in the next frame and produce a confidencemap. The peak of themap, which is given bymean shift, is thought as the new position of the target. To cope with the changes in features of both foreground and background, the component classifier can be discarded or added at any time. The experiments performed on several sequences showed the robustness of the proposed method.关键词：target tracking;AdaBoost;SVM;parameter adjusting strategy;mean shift3182|243|0更新时间：2024-05-07
- 关键词：mathematical morphology;B-Snake;separate-lin3013|203|0更新时间：2024-05-07
-
- 摘要：In this paper, a novel segmentation algorithm is proposed which is based on MOGs and interframe gradient information. Firstly, a primary foreground segmentation is obtained, where an adaptive MOGs(Mixture of Gaussians) is established for each pixel’s luminance; Secondly, luminance and chroma of each pixel change largely due to the abrupt illuminance change, which causes the mismatch between a pixel’s luminance and its MOGs, and causes the misclassification of a vast of background pixels as the foreground as well. To adapt to the illuminance sudden variation, an improved method using the interframe gradient information is adopted to correct the initial segmentation. Finally, morphological methods are used to remove shadows and isolated noise pixels. Experimental results on various video sequences show that thismethod is robust and of high segmentation accuracy.关键词：complicated background segmentation;MOGs;structure gradient cross-correlation;illuminance abrupt variation3229|249|0更新时间：2024-05-07
- 摘要：Representation and detection of deformable Shapes play an important role in image processing. We propose an approach to representing and detecting deformable shapeswith holes. We represent those shapes using shape polygon with holes, which can also express the position relationship efficiently among different curves in those shapes. Appending aided edges what are regarded as two edges without intersection, the shape polygon with holes are transformed to a simple polygon without holes. Then, we get the perfect delete list on this simple polygon by using Constrained Delaunay Triangulation(CDT). Using the modified non-serial dynamics programming, we realize the detection of deformable Shapes. We also provide some test results to verity our algorithm.关键词：shape polygon with holes;aided edge;perfect delete list;non-serial dynamics programming3118|219|0更新时间：2024-05-07
- 摘要：The spatial object and its edge in the RS image possess fuzzy character. Based on the features of fuzzy objects in the image and the cloud theory, the paper studies the representation of fuzzy objects in image. By the gray and gradient or other digital characters of the image, we can construct a spatial object cloud. The fuzzy spatial object can be represented by the object cloud. The edge of the spatial object can be represented by half cloud ring. So fuzzy objects in the RS image can be represented based on the fuzzy mathematics cloud model properly. Experimental results show that the method is both efficient and effective. It enriches the cloud theory, and proposes a new idea for the representation of the fuzzy object and image comprehending and analyzing, especially the remote sensing image.关键词：remote sensing image;cloud theory;fuzzy object;object cloud;half cloud ring2528|285|0更新时间：2024-05-07
- 摘要：The paper proposed a region filling algorithm based on crack chain code description. The algorithm of single crack chain code and a fast filling algorithm about the complicated connecting region or the global image are given, in which only the image regions is filled. Compared with the conventional algorithms, this algorithm requires no storage and works well for any complex regions. Experimental results prove that it is faster and more efficacious.关键词：crack chain code;region filling;filling algorithm3493|205|0更新时间：2024-05-07
- 摘要：This paper analyses the uniform B-spline model with shape parameters, and applys the model to the curve fitting of discrete data points. In this paper, the value of the shape parameter is studied, and an algorithm based on iterative linear closest points is put forward to rectify the parameter values of data points. The analysis of experimental results demonstrates the validity and robustness of our algorithm.关键词：uniform B-spline with shape parameters;curve fitting;iterative liner closest point3036|281|0更新时间：2024-05-07
- 摘要：A segment-based two-step stereo correspondence algorithm is proposed. In the first step, Dynamic Programming and Left-Right Consistency are used to detect ground control points, and the original image is segmented into small areas, where each of them is assumed as a single disparity, mean while the detected GCP are used to compute the disparity value of the part of the image; In the second step, the left unmatched areas are coded as a single chromosome, and are optimized with genetic algorithm to generate the dense stereo disparity map. The algorithm is tested on the standard image pairs, and the experimental results show its good performance.关键词：image segmentation;stereo correspondence;ground control point;genetic algorithm3076|236|0更新时间：2024-05-07
- 摘要：A bidirectional disparity area feature-constrained match method is proposed in this paper. In this method, after feature points of two images extracted, disparity area constraint is designed to reduce candidate match point sets during the process of bidirectional uniqueness constraint correspondence according to the binocular projection characteristics. Then the slipping neighborhood disparity is designed to reject false match points. Experimental results show that the proposed method can be easily implemented for processing complicated scenes and get high precision matching quickly.关键词：stereovision matching;feature correspondence;disparity;projection2897|241|0更新时间：2024-05-07
- 摘要：The Delaunay criterion of the empty sphere is widely used for 3 dimensional tetrahedron tessellation. But original Delaunay tetrahedralization can notbe used for the points set with constrained boundary and the degenerate points set in which four ormore points are coplanar or in which five ormore points are cospherical. The concept of Delaunay tetrahedralization in an arbitrary domain (DTETAD) is presented based on the definition of local optimized triangulation which is brought out to substitute the strict empty sphere criterion of Delaunay. The sufficient and necessary condition for a tetrahedralization to be a DTETAD are proved, and the conditional empty sphere criterion ofDTETAD is presented. The research establishes the theoretic foundation for the application of Delaunay in an arbitrary domain.关键词：Delaunay;tetrahedralization;3-dimensional;arbitrary domain3634|236|0更新时间：2024-05-07
- 摘要：The model reconstruction based on measuring point-sets is a key step in the reverse engineering, it is quite necessary to simplify the measuring point-sets and analyze the reconstruction error in order to improve the reconstruction precision and the reconstruction efficiency and provide essential information for the model reconstruction. In this paper, a new simplification algorithm for measuring point-sets is realized firstly, and then a novel method for reconstruction error analysis where the simplified point-set is fitted by an implicit surface based on compactly supported radial basis function is presented. The experimental results show that the simplification algorithm has higher efficiency and better effect, the error analysis results based on implicit surface can restrict simplification quantity within the limitation of reconstruction precision.关键词：point-sets simplification;implicit surface reconstruction;compactly supported radial basis function;error analysis3033|220|0更新时间：2024-05-07
- 摘要：Triange meshes are widely used in representing surfaces in computer vision and computer graphics. Although a lot of work related to 2D image processing based on edge extraction techniques has been done in many applications, it is not well developed to extract the border of surfaces represented by triangle meshes, especially the visible border along on vector. A detection algorithm of visible mesh borders is presented in the paper. The visibility of a triangle facet in the mesh is determined by the relation between its normal vector and the ray direction. The type of a triangle facet is defined by the number of its visible edges, and it includes 0-type, 1-type, 2-type and 3-type. The visible border is detected according the triangles' typ2. The algorithm's time complextity is O(n). Experimental results demonstrated the feasibility and validity of the algorithm. This algorithm is applied in the shelter calculation for the solar arrays of the satellite configuration analysis. And the requirements on computing velocity and accuracy for engineering application are met completely.关键词：mesh surface;visible border extraction;shelter analysis3511|329|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