最新刊期
卷 16 ， 期 5 ， 2011
- 摘要：This is the fifteenth 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, 782 references on image engineering research and technique are selected carefully from 3251 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 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 2010.关键词：image engineering;image processing;image analysis;image understanding;technique application;literature survey;literature statistics;literature classification.3690|487|0更新时间：2024-05-07
- 摘要：With the popularity of wireless access and video applications, wireless video transmission is bringing more attention. In most papers, the ideas of cross-layer optimization and unequal protection were adopted. To improve transmission quality of wireless video streams, a novel scheduling algorithm which integrates priorities of video frame with “relative queuing delay” and is suitable for any coding algorithm with limited priorities under IEEE 802.11e is proposed in this paper. Simulation results show that average peak SNR of proposed algorithm is much higher than those of EDCA and existing improving scheme.关键词：video frame scheduling;relative queuing delay;unequal protection;priority mapping3011|202|0更新时间：2024-05-07
- 摘要：A concept of image compression based stratified variable blocksize decomposition is proposed after analyzing current image compression algorithms compreehensively. As the current most popular methods for static image compression, JPEG, JPEG2000 and fractal perform similarly when compressing different images with the same compression ratio: the more visually complex an image is, the lower a restored image quality is. After a large number of experiments, previous work shows that there is a clear relationship between all the three methods and image activity measure (IAM). According to the complexity of different image regions, stratified variable blocksize decomposition (SVBD) is achieved, using IAM and similarity as performance index. Particle swarm optimization (PSO) algorithm is used to find optimal approximation of the image blocks. Finally, by classifying the image blocks, some improvement to compression quality can be made.关键词：image activity measure(IAM);image decomposition;stratified;variable blocksize;PSO;image compression2986|280|0更新时间：2024-05-07
- 摘要：Image super-resolution refers to reconstruction of a high resolution image from one or a set of blurred low resolution images. This paper only pays attention to the kind of reconstruction from one blurred low resolution image. Many methods have been developed for this kind of reconstruction, most of which are MAP methods and interpolation methods. This paper proposed a new interpolation method. The proposed method used the quad tree segmentation to partition the low resolution image, the edge-directed interpolation to each segmented band of the low resolution image, and a wavelet projection to optimize the high resolution image obrained from the local interpolation. The experiment used the peak signal to noise ratio (PSNR) to compare the reconstructed image with the original image. And the results showed that the PSNR and visual effect of the high resolution image reconstructed with the proposed method were very good.关键词：wavelet transform;least square approximation;self-similarity;super-resolution3799|254|0更新时间：2024-05-07
- 摘要：An integrity authentication scheme for video bit-stream based on the fragile watermarking is proposed in this paper. In the compressed bit-stream of H.264, The authentication codeword are generated according to the mode of intra_4×4 in I_Slice firstly, and then embedded into B_Slice and P_Slice by modulating some VLC codeword of sub-block. This modulation is based on the mapping rule between the VLC codeword and the bit to be embedded. The mapped codeword is very similar to the original codeword, namely, the length of codeword is same and the value of coding element is similar. This scheme could detect the watermarking rapidly, which meets the requirement of the real-time processing of video. Experimental results show that it has less influence on the quality of video, and can effectively carry out the integral certification of video frame.关键词：video watermarking;VLC;integrity authentication;codeword mapping;Exp-Golomb coding3213|212|0更新时间：2024-05-07
- 摘要：In this paper, the similarities of bits, reference frame selection and coded block pattern(CBP) of a coding macroblock(MB) between each inter mode and optimal mode have been investigated. The bits and CBP’s distribution characteristics of a MB which encoded by the optimal mode have been analyzed, and the result shows that the coding modes can be differentiated by bits and CBP. Based on these characteristics, a novel low complexity rate distortion optimization (RDO) algorithm which combination reference frame selection with mode selection RDO is proposed. This algorithm utilizes P16×16 mode’s reference frame to select the candidate reference frames for other inter coding modes, and the candidate modes are selected by bits and CBP of mode P16×16. The optimal mode will be selected in all candidate reference frames and candidate modes with RDO. The algorithm is evaluated using a wide range of test sequences of different classes. Comparing with RDO in JM12.0, the experiments results demonstrate a reduction coding time 71.20% in average with 1.32% of bits increase and 0.0752dB of Luma PSNR loss.关键词：video coding;RDO;MB coding characteristics3120|189|0更新时间：2024-05-07
-
A FPGA implementation of integer discrete consine transform and quantification for H.264 compression
摘要：Due to its excellent compression rate and high image quality, H.264 is widely applied in many regions, such as real-time internet video communication, digital television broadcast, HDTV and so on. As a key component of the H.264 coding framework, integer discrete consine transform(IDCT) and quantification module takes on the rule of reducing the correlation coefficients of input data, which is an important pre-processing before the entropy coding. The normal realizations are based on software or hardware co-processor, in which way speed and throughput are limited. As a contrast, realization based on hardware can make up these shortages. In this paper, an FPGA implementation of integer discrete consine transform and quantification for H.264 compression is introduced, which is based on a high throughput structure and is accomplished by register-transfer level (RTL) description. The whole design is tested on the Cyclone Ⅱ-based development board, DE Ⅱ. The resource cost is 10489 LEs. Its maximal work frequency is 184.88MHz, the maximal throughput is 2958Mpixels/s, and it can process a 4×4 input data within a single clock period.关键词：IDCT;quantification;H.264 compression standard;FPGA3551|222|0更新时间：2024-05-07 - 摘要：The video error detection is the basis of error concealment, which is studied in a typical application scene in this paper. At first, the error detection algorithm based on spatial feature is improved to adaptively adjust the decision threshold. Then, the feature of video temporal correlation is introduced, and a novel joint space-time video error detection algorithm based on prior restrictions with better applicability is proposed. Finally, the algorithm is simulated in 3G video communication environment, the results indicate that the proposed algorithm has a higher accuracy and provided a reliable basis for error concealment.关键词：error detection;syntactic detection;space-feature detection;time-correlation detection;joint space-time;3G2440|200|0更新时间：2024-05-07
- 摘要：Image segmentation plays an important part in the areas of multimedia, image processing and computer vision. In the paper, the authors propose an image segmentation approach based on an entropy measurer. Specifically, the image segmentation entropy (ISE) is defined to describe the information of an image region. We further prove that the image after segmentation have the minimum ISE, if the image is correctly partitioned. Then, the image segmentation problem is cast into an optimization problem which minimizes ISE. Finally, we use the iterative graph cut approach (IGCA) to solve the optimization problem. The experiments provided in the paper show that our ISE based segmentation approach works well.关键词：image segmentation entropy;iterative graph cut approach3505|272|0更新时间：2024-05-07
- 摘要：Because of the disadvantages of Multi-resolution Markov random field in wave domain for the description of the nonlinear features of the image, this paper proposes a new Multi-resolution Markov random model in morphological wavelets domain to partition the texture images. Morphological wavelets can do a nonlinear multi-resolution decomposition of images. Markov random field can model the spatial relationship of pixels in each resolution. The multi-resolution Markov random model in morphological wavelets domain combines the benefits of morphological wavelets and Markov random field. The experiments of texture images segmentation validate of our model, where the test texture images are employed from the Brodatz and Prague texture image databases.关键词：morphological wavelets;Markov random field;segmentation;texture2946|243|0更新时间：2024-05-07
- 摘要：An approach for image segmentation based on visual saliency is proposed in this paper. First low-level visual features of the image are extracted. Local saliency, global saliency and rarity saliency are computed for each feature map to get the feature conspicuity maps. Then these conspicuity maps are integrated to generate the saliency map. The saliency map is segmented using a threshold and a binary mask map is obtained. Finally the foreground and background of the original image are separated by adding the binary map to the original image. The proposed model has been tested on many natural images. Experimental results show that the proposed approach is valid and the segmentation results are consistent with human visual system.关键词：image segmentation;visual attention;saliency map;threshold5082|367|0更新时间：2024-05-07
- 摘要：In this work, we propose a natural image segmentation method based on unsupervised fuzzy C-means (USFCM) clustering algorithm. The intersection of confidence intervals rules is utilized to adaptively compute the scale of Gabor filter for each pixel. Then image features are measured by Gabor filter with adaptively computed scale, orientation, frequency and phase. Meanwhile, a fast polynomial segmentation method is proposed to determine the number of clusters. Then the algorithm USFCM is utilized to get the final segmentation. The experimental results show that the proposed method can overcome the impact of texture and distinguish the target from background. The performances have demonstrated the effectiveness, accuracy and superiority of the proposed method.关键词：nature image segmentation;unsupervised clustering;FCM;Gabor filter;intersection of confidence intervals (ICI);texture features3641|725|0更新时间：2024-05-07
- 摘要：Traditional clustering algorithms are always viewed as unsupervised methods for data grouping to extract information of interest from unlabeled data, while semi-supervised clustering employs limited amount of labeled data to aid the unsupervised grouping of mass unlabeled data. Pedrycz provided a semi-supervised Fuzzy C-Means algorithm (sFCM) to incorporate supervised information of labeled data as an additive part of objective function in the Fuzzy C-Means algorithm (FCM).This paper proposes a novel algorithm called Degeneracy-Improved Semi-Supervised Fuzzy C-Means algorithm (dsFCM) to fundamentally overcome the critical disadvantages of Pedrycz’s sFCM algorithm, i.e., degeneracy to the classical FCM algorithm and slow convergence, particularly when applied in actual data set in which the amount of labeled points is far fewer than that of unlabeled points. Experimental results on UCI benchmark data and IBSR brain MR image data demonstrate that dsFCM algorithm can outperform sFCM algorithm in accuracy, speed and robustness. Moreover, it shows that dsFCM algorithm avoids the problems of slow convergence and degeneracy to classical FCM algorithm when applied to real world data clustering with exiguous labeled data, and presents its effectiveness for the application in interactive segmentation of medical images with a small amount of labeled data points given by user.关键词：clustering;semi-supervised learning;image segmentation;FCM;seed clustering3646|271|0更新时间：2024-05-07
- 摘要：Unstructured road region detection forms a main problem of environment sensing for intelligent vehicle. In this paper, two learers are proposed to solve this problem. One is a support vector machine (SVM) classifier which utilizes multi-orientation Gabor texture histogram, and the other is a color histogram back-projection model. Both learners are combined in a co-learning framework. In practical running, the two learners can provide “labeled” samples for each other. This approach can improve the online learning capability and avoid the model drifting problem which often occurs in self-learning approach. Experimental results show the advantages of the proposed co-learning approach.关键词：co-learning;road detection;support vector machine2981|213|0更新时间：2024-05-07
- 摘要：With the growing use of face recognition in security and video control domain, there are growing concern about security and privacy of biometrics data. This paper proposes a security algorithm about face feature, which bases on the SIFT feature and random projection. Because the SIFT features are invariant to image rotation, scale and change in illumination，feature extraction is first performed on face images by SIFT algorithm. The SIFT features are transformed using invertible transformation which is generated by user specific key. All the above successive procedures produce the cancelable and non-invertible template feature data, which can achieve the protection of face data. In extensive experiments with publicly available face datasets CMU, AR and Feret, higher recognition accuracy is reached, which demonstrates that the proposed approach is not only able to protect the face data, but also robust to various complex conditions, such as changes in the pose, occlusions and expression, etc.关键词：face recognition;SIFT;security;privacy;robust3402|255|0更新时间：2024-05-07
- 摘要：This paper explores a new 3D palmprint recognition mehthod. We aim to improve the accuracy and robustness of existing 2D palmprint authentication using 3D palmprint curvature information. First, the curvature is an important characterization of 3D Objects, which can present the shape of local surface has nothing to do with the view point. No matter how the palm rotates or translates, the curvature is stable. So the mean curvature of 3D palmprint is used to depict the surface feature of 3D palmprint. Next, we obtain the surface curvature map as 2D gray images mean curvature image (MCI). Then, using the RLDA method extracts the second feature in order to eliminate the existing problems of traditional LDA—small sample size problem and the problem that optimization criterion function is not directly related to recognition rate. Experiments, show method presented in this paper has a higher accuracy compared with traditional LDA, PCA, ICA and LPP etc.关键词：3D palmprint recognition;mean curvature;RLDA3341|211|0更新时间：2024-05-07
- 摘要：This paper describes a real-time people counting system, which combines the pedestrian detection and tracking method together for people counting. The normalized MB-LBP feature, which can be easily calculated and suitable for multi-scale detection, is adopted for detection in the foreground at the detecting stage. The points are grouped together with a probability model to track the pedestrian at the tracking stage. At the same time, these points are employed to map the detected pedestrian to the tracked pedestrian. And in order to verify the performance of the system, three experiments are designed for testing. The first two videos are captured at different locations with different backgrounds; the third video, which has been used for testing in many other papers, is used for comparison. The experiments results demonstrate that this system performs the function of counting well at different background situations.关键词：people counting;pedestrian detection;object tracking;feature points4164|290|0更新时间：2024-05-07
- 摘要：Infrared small target tracking is susceptible to similar target and background. To address this problem, an algorithm for infrared small target tracking based on gray and velocity cue integration is proposed. The algorithm enhances the target with high pass filter, and calculates velocity of target by principal component analysis. Target tracking is achieved by a cascade particle filter which consists of two stages of importance sampling. At the first stage, the states of target are crudely estimated with gray kernel histogram in high pass filter space. The velocity cues are used to precisely calculate the states of target in the second stage. The experimental results show that the proposed algorithm has stronger ability to resist to interference of noise, and significantly improves the tracking accuracy in comparison with existing tracking algorithms.关键词：velocity cues;principal component analysis;layered particle filter;infrared small target tracking3607|251|0更新时间：2024-05-07
- 摘要：The mixture of Gaussian method (GMM) proposed by Stauffer et al and its improved versions achieve better performance and have been widely used in smart vision systems. Traditionally, GMM only uses a single color visual feature to model scenes, but it will fail when moving objects have the same color appearance with scenes’ color appearance.In addition, traditional GMM can’t effectively solve problems caused by lighting changes and especially lighting sudden changes. To overcome these weaknesses, in this paper, a new modeling method based on multi-category visual features (i.e. color, texture and edge) is proposed. Experiment results show that our new method solves the above problems effectively,which will be a baseline for high-level vision analysis.关键词：multi-category visual features;DCT;mixture of Gaussian model;precision ratio;recall ratio2875|283|0更新时间：2024-05-07
- 摘要：The simulation and prediction of permeability image are quite significant to the development of oil fields. Because the accuracy of permeability can be improved by integrating conditional data including soft data and hard data, a method based on continuous multiple-point geostatistics (MPS) is proposed to improve the accuracy of permeability in a simulated permeability distribution image. First, filters can reduce the dimensions of permeability images to create a “filter score” space. Second, “filter score” space is partitioned by a two-step partition method to obtain the patterns of each non-empty class and forms a “database” of patterns. Finally, a known pattern is drawn from the above “database” of patterns by a self-defined distance function to achieve a simulated value for an unknown node. The simulated images were compared, showing that the structural characteristics of the permeability image simulated by using both soft data and hard data as conditional data are most similar to those of real data from the training image because of the usage of abundant conditional data.关键词：multiple-point geostatistics;soft data;hard data;permeability;filter;variogram2728|418|0更新时间：2024-05-07
- 摘要：Using the distribution relations between the coordinates of the points on shape contour and the centroid of the shape to describe a shape, a novel shape descriptor CPDH (contour points distribution histogram) is proposed under polar coordinate. This descriptor not only satisfies the human’s visual perception and easy to be calculated, but also it essentially has the properties of invariant to scaling and translation. We also suggest using the Dynamic Programming Algorithm to measure the distance between CPDHs, and that the DP algorithm can partly solve the need of the CPDH’s invariant to rotation. With a great deal of experiments in several shape databases, it is shown that this algorithm, used in image retrieval of shape with a single closed contour, can get favorable results.关键词：shape;contour points distribution histogram;image retrieval;dynamic programming algorithm2855|232|0更新时间：2024-05-07
- 摘要：Feature points searching or point correspondence matching is a challenge in computer vision and pattern recognition, which is very important perquisite for many 2D/3D applications such as image registration，object recognition and statistical model construction. In this paper, we propose an algorithm for facial feature points matching among 3D point cloud models. Specifically, the surface points are clustered based on relative angle context (RAC) features, and then the geometric features of the clustered points are extracted. Afterwards, supported Vector Machine based classification is employed for final accurate correspondence location. The experimental results demonstrate that our algorithm achieves better performance than RAC algorithm proposed.Within the confines of a given distance threshold, the accuracy rates of 50% feature points have even reached to 100%.关键词：relative angle-context distributions;support vector machine;feature points locating;K-means3103|223|0更新时间：2024-05-07
- 摘要：This paper presents an efficient algorithm for extracting faces from polyhedral wireframe models. The main features of the algorithm are using the topological and geometric information of wireframe models and its stronger adaptability. First, the wireframe model is projected to a plane, and the “invisible” edges which are obstructed by another edge in projection are hidden. And the edges which have a common vertex are arranged into a set in counterclockwise. Then search the minimal circle based on rule of the smallest rotation angle in clockwise. At the same time the Moebius rule are use to delete the illegal circle and remove the finished edges which are accurately contained by two circles. When a “visible” edge is removed, “invisible” edges blocked by it may be “visible” ones. So the new minimal circle can be searched. Repeat this course until all edge is removed and there are no illegal circle and illegal edge. Finally，the remaining circle are all true face of the model and all point to outside of the object by adjusting their direction. Several typical examples are given to demonstrate the widespread adaptability and high efficiency of the algorithm.关键词：wireframe models;face identification;projection;circle3020|182|0更新时间：2024-05-07
- 摘要：In the area of multi-focus images fusion, the multi-resolution coefficients fusion algorithms can not extract the clear pixels from source images, and the block extract algorithms always cause block effects. Therefore, the authors define the image pixels’ regional contrast based on stationary wavelet transform (SWT), which is non-subsampled and translation invariant, considering the characteristics of the clear pixels in multi-focus images and the contrast features of human visual system. On the basis of studying how different neighborhood sizes of regional contrast can affect the correctness of extracted pixels, a proper threshold is set to build extraction templates, which are used to extract pixels in the clear region in source images. Then, the method of image fusion based on local energy mechanism is applied to those un-extracted pixels. The experimental results illustrate the novel algorithm in the paper can not only effectively extract the clear pixels from source images, but also reduce the block effects greatly, and the quality of the fused image is improved sharply.关键词：multi-focus;image fusion;SWT;regional contrast;extract pixel3511|221|0更新时间：2024-05-07
- 摘要：The point distribution model is a powerful shape description technique and has enormous applications in a short time, especially for flexible or deformable model analysis in images. Initially, a model is generatively built by statistical analysis from a number of examples. In some applications, nevertheless, it allows building a set of models or continuous sequence of models since a single one is not well representing a highly changing object. This paper presents a method to compute such a middle time-point model which is formed from two neighboring models in runtime. In case of linear algorithm, the model parameters that have already given by PCA are determined in several steps. The methodology is validated with both computer simulation and practical experiments. Results indicate that it is worthwhile for its adoption in some complex modeling applications.关键词：point distribution model;middle model;ASM;AAM;deformable model;image processing2891|185|0更新时间：2024-05-07
- 摘要：Statistical shape model (SSM) is an efficient method of image processing and analysis. One key factor in building models is to obtain correspondent landmarks among the whole shape dataset. Traditional manual land-marking is temporally expensive, subjective，boring and prohibitively extensive in dimension. In this paper, a multi-scale parameterization on shapes allows a minimum description length (MDL) based optimization on landmark correspondence in a coarse scale and a most convenient arc parameterization based landmark correspondence in a fine scale. This achieves a fast and accurate SSM building, which is the foundation on following image segmentation and quantitative analysis. In experiments, SSMs are built with vertebral body, intervertebral disc and meniscus shapes extracted from various MRIs respectively. It is testified that the models built with the proposed scheme is not only more repeatable and concise than model baseds on manual landmarking, but also more temporally efficient than model purely based on optimization. The segmentation errors from the proposed method are comparable with or better than those from the manual modeling based segmentation.关键词：statistical shape models;minimum description length;point correspondence problem;automatic landmarking4373|223|0更新时间：2024-05-07
- 摘要：The irregular surface registration is a challenging issue in the three dimensional registration. This paper proposed an approach to point cloud coarse registration by using the distance between an irregular surface point and the center of mass of its one length neighboring points as the rigid feature, and to point cloud fine registration by the iteration close point algorithm and rigid feature. The experimental results show that the error convergence rate of the rigid feature iteration close point algorithm is significantly improved. And then, both the convergence rate and the registration quality of the algorithm are improved, compared with iteration close point algorithm that not have coarse registration, when point clouds which the distance between the center of gravity is bigger than 10.关键词：irregular surface;feature registration;center of mass distance feature;iteration close point algorithm3858|246|0更新时间：2024-05-07
- 摘要：An improvement to quadric-error-metrics-based mesh simplification algorithm is presented in this paper. Firstly， the support region on the original mesh is defined for the new vertex generated in an edge collapse operation, and the connection between the new vertex and the original mesh is established. Secondly，the quadric distance error from the new vertex to its support region is calculated as the global simplification error, and the original quadric error is regarded as the local simplification error; Finally the sum of the two errors is defined as the new cost function of the edge collapse operation. Experimental results demonstrate that the improved algorithm can preserve the details better than the original one and reduce the simplification error obviously.关键词：mesh simplification;support region;global error;quadric error metrics;edge collapse3497|237|0更新时间：2024-05-07
- 摘要：Based on the idea of energy optimization, a new method for shape modification of the B-spine curve is proposed. First, using an analogy between the B-spline curve and the curve element of finite element method, and making the external load acting on the curve be equivalent to the end force into the element, the internal energy functional equation of the B-spline curve and the energy functional equation of the load are constructed respectively. The energy change of the B-spline curve with the change of the load, a new curve is generated by solving an optimization problem of the change of the energy. Using this approach, the local or total modification of the curve can be accomplished.关键词：B-spline curve;shape modification;energy optimization;energy model3198|182|0更新时间：2024-05-07
- 摘要：It is known that how to organize effectively geodata of mobile device in LBS（location based services）are organized ineffectively. So after the existing solutions are compared and extended in the paper, a new SVG(scalable vector graphic) based solution is provided to represent and compress spatial data. Then the key technologies in the fields of SVG data representation and compression are researched and resolved, in which the improved compression method combined simplified SVG representation and GZIP compression. The test result showed that SVG based method is appropriate to represent geodata in LBS, and the improved method to compress SVG based data is better than traditional method, in which the feasibility of the solution is validated.关键词：location based services (LBS);scalable vector graphic(SVG);representation;GZIP;SVGZ2812|198|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