最新刊期
卷 17 ， 期 5 ， 2012
- 摘要：This is the seventeenth annual in the survey series annual 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,797 references on image engineering research and technique are selected carefully from 3 215 research papers published in 134 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 (same as the last 6 years). Some analysis and discussions about the statistics made on the results of classifications by journal and by category are also presented. This work shows a general and off-the-shelf picture of the various progresses of image engineering in China in 2011.关键词：image engineering;image processing;image analysis;image understanding;technique application;literature survey;literature statistics;literature classification;bibliometrics3434|227|0更新时间：2024-05-08
- 摘要：Photorealistic modeling of plants appearance is an important research area in computer graphics. Plant leaves receives wide attention as the most important plant organ. Recently,by the rapid development of computer hardware and graphics algorithm and deep research in physiological structure of plant leaves,appearance modeling and photorealistic rendering of plant leaves has reached many good results. Especially,the acquisition of reflectance properties of plant leaves and appearance modeling are hot research topics. Starting from the definition of a photorealistic appearance model,we review the newest research development in plant appearance model and photorealistic rendering algorithm in China and abroad,and we analyze all kinds of algorithms. In the end,we summarize some problems in this research field and proposes an outlook and trends.关键词：appearance model;plant rendering;photorealistic rendering;plant leaf modeling3417|124|0更新时间：2024-05-08
- 摘要：To overcome the attacking-prone drawbacks of quantization index modulation(QIM) in YASS(yet another steganographic scheme),an improved YASS algorithm based on MSBs(most significant bits)arithmetic decoding in DCT domain is proposed.First,a secret sequence is viewed as an arithmetic coding stream and recovered by arithmetic decoding with the MSBs probability of a cover signal distributed,thus the codec reset results in a same marginal distribution between decoding stream and the cover.Then,the decoded bits are reembedded as the convention.Combined with the highly random embedding of YASS,the proposed scheme has a higher security with the first order distribution historgram between the cover and the stego minimized.Experiments demonstrate that the proposed method outperforms YASS both in capability of anti-steg-analysis and the performance of coefficient distribution historgram, which is 6.8% for YASS and 6.3% for the improved one in average. It is an effective steganographic algorithm.关键词：steganography;yet another steganographic scheme;most significant bits probability;arithmetic decoding3132|119|0更新时间：2024-05-08
- 摘要：The non-localmeans(NL-means) algorithm provides a powerful framework for removing Gaussian noise. However,it is computationally impractical. In order to accelerate the algorithm,we use a moving average and weight symmetry in this paper. Speeding up the algorithm sometimes may reduce the quality,so we propose a modified weight function for calculating the weights. Finally,numerical results reveal that the proposed algorithm is faster than the original non-localmeans,and is also very competitive to most of the state-of-the-art algorithms in terms of both the PSNR and the subjective visual quality.关键词：image de-noising;non-localmeans;moving average;robust M-estimator4200|155|0更新时间：2024-05-08
- 摘要：To improve images degraded by smoke,a homomorphic filter algorithm based on lift-wavelet transform is used to enhance the contrast of an image. In this paper,we use a homomorphic filter algorithm based on lighting reflection models and develop an applicable filtering model and expression. Secondl,we take lift-wavelet transform into the homomorphic filtering and process the wavelet transform coefficient by using high-pass filtering,aiming to improve the processing speed. Finally,six different objective evaluation parameters are used to evaluate the disposed images. The results reveal that the algorithm is move effective than homomorphic filtering and equal with wavelet homomorphic filtering,which is slower than our proposed algorithm.关键词：lift-wavelet transform;homomorphic filtering;filter in frequency;smoke weakening3746|137|0更新时间：2024-05-08
- 摘要：The watershed algorithm is a powerful morphological tool for image segmentation,but the traditional watershed algorithm causes serious over-segmentation if the actual image is affected by specularities and shadows. To solve these problems,a new image segmentation,based on reconstruction labeling watershed algorithm in color space,is proposed. First,the RGB color image is converted to a new color space image. The directions that are not influenced by specularities and shadows are extracted to calculate their gradients. Then,object regions are extracted by using the morphological opening and closing to compose a binary marked image,and the gradient image is introduced to substitute the marked image. Finally,the watershed transformation is employed to the modified gradient image. The new algorithm cannot only overcome over-segmentation,which is produced by texture details and noise,but also can suppress over-segmentation caused by specularities and shadows. Moreover,the segmentation algorithm is executed on a primitive gradient image instead of filtering and simplified image,so the object's edge information is retained greatly. Theory analysis and experimental results have shown the segmentation algorithm is effective.关键词：image segmentation;specularities;shadows;color space;reconstruction labeling;watershed4031|131|0更新时间：2024-05-08
- 摘要：A new algorithm of non-rigid cell tracking based on balancing feature matching is proposed. A probabilistic model is established and solved using Random Walks with Restart (RWR). An efficient method for bidirectional balance is presented to balance the adjacency matrix of RWR,and then a precise matching between objects under different deformations is completed. The position tracking is accomplished based on the matching results. At the same time,an automatic calibration to object is presented with the results of the feature matching. A precise object contour tracking is presented with a method for image segmentation. We prove by experiment that the method shows good performance in the conditions of high background similarity and fast moving objects when used for tracking moving cell under dynamic background in videos. More accurate localization and target contour description can be obtained compared with other methods.关键词：balanced probabilistic model;feature matching;image segmentation;object localization;cell contour tracking2673|91|0更新时间：2024-05-08
- 摘要：Focusing on blob features that usually appear in images,we developed a method for detecting their positions and size automatically. The main work includes: 1) An extreme energy function for detecting blob features,which is constructed based on the gradient distribution of blob features;2) A theoretical analysis made on the property of extreme energy function,and then an intuitive analysis of its extreme property is made based on simulated images; 3) The implementation of the algorithm for detecting positions and sizes of blob features is proposed; 4) Experiment results showing that the method proposed in this paper can effectively and exactly detects positions and sizes of blob features in images,and the method performs stable and robust under noise,image blur,and viewpoint changes.关键词：blob feature;position and size detection;extreme energy function;three-dimensional extreme energy space3133|133|0更新时间：2024-05-08
- 摘要：A new edge detector based on an improved polarimetric whitening filter (PWF) for polarimetric synthetic aperture radar (SAR) images is proposed,aiming at a better usage of polarimetric information and reducing the speckle noise. The covariance matrices of the background and the center in PWF are replaced by those at both sides of the moving edge template. Polarimetric information including complex correlation between different polarizations is better utilized while speckle is suppressed at the same time. The new method is demonstrated using simulated and real polarimetric SAR data.关键词：synthetic aperture radar;polarimetric whitening filter;edge detection;speckle2907|95|0更新时间：2024-05-08
- 摘要：In this paper,we present an approach for detecting pedestrians from moving backgrounds which is based on compound features combined with motion and static features. It is difficult to discriminate human bodies from a moving background. We improve Nagel's second-order gradient optical flow algorithm and enrich the inner repeatability of MBH (motion boundary histograms) and IMH (internal motion histograms) motion feature based on the flow. We train a linear SVM (support vector machine) classifier using features made from a pedestrian sample. A fixed window sliding over image and classify results are optimized using the mean shift algorithm. The accuracy is 98% on test of 1 093 group images,which is better than the results using other methods.关键词：pedestrian detection;second-order gradient optical flow;motion feature;support vector machine;mean shift3307|156|0更新时间：2024-05-08
- 摘要：In order to eliminate the effect of varying illumination on face recognition,a novel illumination invariant method based on the Gabor phase-frequency feature is proposed.The method first performs illumination normalization on image under various lighting conditions,which can reduce the effect of varying illumination to some extent.Secondly,a set of 2D real Gabor wavelets with different directions are used for image transformation,and multiple Gabor coefficients are combined into one whole in considering spectrum and phase.Lastly,the illumination invariant is obtained by extracting the phase feature from the combined coefficients.Experimental results on the Yale face database B and on the CMU PIE database show that the proposed method can effectively eliminate the effect of varying illumination on face recognition,and that extracted illumination invariant is robust.关键词：Gabor filter;phase-frequency feature;illumination;face recognition3152|142|0更新时间：2024-05-08
- 摘要：Shape feature extraction from an image usually suffers from effects like imaging noise and segmentation errors. A robust shape description algorithm is therefore a prerequisite. In this paper, relations between performances on elastic quadratic wire (EQW) based shape representation model and the model parameters are revealed first. By taking advantage of these relations, we focus on building a new EQW model that adaptively preserves geometrical features. Then the proposed EQW model is further embedded into the Live Wire algorithm. In experiments, the improved Live Wire algorithm is tested on medical and remote sensing image segmentation. Qualitatively, the results show that the proposed model has better performances on extracting object boundaries while avoiding meaningless morphology caused by noisy or incomplete data. Quantitatively, the segmentation errors and the temporal cost of the improved Live Wire are both acceptable.3390|96|0更新时间：2024-05-08
- 摘要：In this paper we put forward a simple and efficient color mapping method to improve the sufficiency of nearly color night vision schemes based on global statistics.First,multi-band images are fused into the three components of an RGB image in terms of a simple linear fusion strategy based on the opponent property of ON-center OFF-surround reception in biological vision.Then a color clustering method is applied to produce color fields in the fused image.The corresponding fields in the reference image are obtained by locating the pixels in the fused image and finding the corresponding pixels in the reference image.Finally,the local mapping in the simplified Lab color space optimizes the match between the night vision and the reference images.Experiments have shown that the proposed scheme can yield a night vision image with a natural daytime color appearance while also improving the speed.关键词：coloring night-vision;color mapping;color space;image fusion4548|81|0更新时间：2024-05-08
- 摘要：In this paper,we introduce a new algorithm for estimating camera pose from point correspondences.Generally,the camera pose problem could be formulated as an optimization problem.The current methods transform the problem into a set of second order cone programming (SOCP) feasibility problems which obtain the global optimal solution by searching the rotation space.In this paper,by relaxing the second-order cone constraints to linear constraints,we propose an improved method that combines branching and bounding with linear programming (LP).Our method cannot only get the global optimal pose but also runs two times faster than the curreut best method.Our approach has been tested on a number of synthetically generated and real data sets,and the results demonstrate the accuracy and the high speed of the proposed method.关键词：pose estimation;global optimization;branch and bound;linear programming;second order cone programming2584|87|0更新时间：2024-05-08
- 摘要：Traditional methods for Content-based Object Retrieval usually employ extracting and comparing local features, which are too computational demanding and require offline training process. Therefore, a novel real-time CBOR method based on dominant orientation templates (DOT) is proposed. Besides, the proposed method makes use of the spatial distributions of grid scores to construct likelihood maps and utilizes a pyramid-scoring strategy to dispose the false windows in which the grid scores are dispersed. With the above improvement, the implementation for CBOR is able to retrieve the query target directly from the videos without offline training. The results show the proposed method improves the retrieval performance while retaining real-time processing ability of DOT matching.关键词：content-based object retrieval;dominant orientation templates;likehood map;pyramid-based scoring strategy3700|114|0更新时间：2024-05-08
- 摘要：The similarity of curves has wide applications in computer graphics.In this paper we provide a quasi-curvature based method for measuring curve similarity.In principle,the new method works under rotation,translation and proportional zooming.The parameter intervals of the similar sections between two different curves can be calculated at the same time.Experiments illustrate the effectiveness of the new method in applications such as image stitching and image object retrieval.关键词：quasi-curvature;similarity;image processing;spline curve3569|110|0更新时间：2024-05-08
- 摘要：Visual range assessment is an important part of the ergonomics analysis.In order to get achieve visual effects for the visual range assessment,we construct a translucent model of the human eyes' visible range and bind it to the bones of the ergonomic virtual human.Then,a real-time dynamic visual range evaluation is achieved by using real-time blend rendering technology.As an example,the gantry CNC machining center design model is taken to demonstrate the effectiveness of the method.It shows that the vivid visualization analysis not only makes the ergonomics analysis simple,fast, and visible,but also avoids many manual operations,improving the speed of the analysis,and reducing the human errors.The method can be applied in the practical engineering directly and it can support the visibility analysis of various types of layout design.关键词：human engineering;visual range assessment;virtual human;visualization2642|78|0更新时间：2024-05-08
- 摘要：The noise analysis and elimination in remote sensing images has attracted considerable attention,and has become an important research field for remote sensing image processing. In this paper,we propose a wavelet threshold method to de-noise the Gaussian noise in remote sensing image to make the edge fuzzy causing by over the existence of the "strangulation" of the wavelet coefficients,as well as P-M model usually tends to make the image gray sub-constant,resulting the so-called "massive" effect problem,This paper proposes a new remote sensing image denoising model based on wavelet partial differential equations (PDE) to address the above mentioned issue.This model decomposes remote sensing images by wavelets and maintain the low-frequency subband information.Only with noise and the edge's high-frequency sub-band based on sub-band directional characteristics of the nonlinear anisotropic diffusion,this model can remove Gaussian noise well and,at the same time,can also protect the edge features and details of remote sensing image,and avoids to appear the piecewise constant phenomenon.Experimental results show that our model gains 1~2dB higher PSNR than the class of zero-tree based on Bayes model threshold and P-M model.关键词：remote sensing image;wavelet directional subband;partial differential equation;P-M model;Gaussian noise3089|119|0更新时间：2024-05-08
- 摘要：The intensity distribution of most original remote sensing images concentrated in a narrow range,resulting in unclear image details and low contrast of the image. Histogram equalization is commonly used to distribute the gray levels of an image uniformg which can increase the contrast of images and enhanced the details. Through the elaboration of the definition of comentropy,we draw forth the image enhancement algorithm of histogram equalization. Then,we put forward an improved algorithm of ideal histogram equalization,which is based on piecewise mapping thoughts through the analysis of the defects existing in the traditional histogram equalization. In addition,we relate and analyze the implementation of the improved algorithm in this paper. Meanwhile,in order to do the quantitative analysis and comparison between the traditional algorithm and the modified algorithm,we use synthetic average contrast,and details evaluation parameters,which are based on simultaneous contrast,the contrast resolution limit,and fuzzy mathematics.Finally,we use simultaneous contrast,synthetic average contrast,and details evaluation parameters as the indexes of quantitative evaluation and quantitative evaluation of the improved algorithm. The results of quantitative evaluation show that the image enhancement effect of the improved algorithm proposed in this paper is better than the algorithm of traditional histogram equalization.关键词：ideal histogram equalization;simultaneous contrast;synthetic average contrast;details evaluation parameters3246|120|0更新时间：2024-05-08
- 摘要：Traditionally,buffer zones of point features are circles with multiple radii. This means that same effect is used within the same radius around a point feature. In fact,a region affected by a point feature is possibly a sector buffer zone,not a circle,due to affecting factors such as wind direction,mountain range,ocean,transportation and so forth. The objective of this study is to enrich the theory and method of buffer zoning in GIS spatial analysis so as to meet the need of analyzing sector buffer zone for point features. Sector buffer zones are discussed with respect to its definition,data structure,fundamentals,algorithms and possible applications. To analyze point features with sector buffer zones,we developed a module using Visual Basic.NET and ArcObjects within ARC\INFO 9.3. After creating a polygon layer,iteratively,the layer field values are read iteratively,and the coordinates of the arc endpoints and chord length are calculated. Then the arc and the two edges of the sector were added,respectively,into the instance defined by an ISegmentCollection which then is assigned to a feature shape. If necessary,the overlaing polygons are handled. Sector buffer wizards with five forms were developed to select different methods and parameters conveniently according to different demands. The wizard provides more choices including the selection of features,radii,central angles,and initial angles. This module can append to ArcMap or ArcToolbox to use it conveniently,automatically,and dynamically. To validate the practicability,applicability,and effectiveness of sector buffer zones,two examples are used for demonstration. One uses sector buffer zones of video cameras distributed on the crossing roads in Kaifeng City,Henan Province,China. The other example analyzes the relationship between rural household income and rural migrant workers in Huangzhuang Village in Zhenping County,Henan Province,China,using the sector buffer zone method. A circle buffer zone is a special case of a sector buffer zone when the central angle of the sector is equal to 360°. Sector buffer zone is an expansion of the circle buffer zone. Results indicate that sector buffer zone,compared to circle buffer zone,has more information and regularities. It is very convenient for the analysis of point feature to reach more credible conclusions and to make decisions for administrators more accurately. In the future,more methods for drawing buffer zones with respect to point features,polyline features,and polygon features will be studied to make buffer system more robust and more perfect so as to meet the need of spatial analysis.关键词：ArcObjects;point feature;sector buffer;GIS3078|73|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