最新刊期
卷 18 ， 期 10 ， 2013
- 摘要：Human palm-vein is a permanent and unique physiological feature for each person. It hides under the skin and is difficult to duplicate because of its complex structure. Furthermore, palm vein images are difficult for candid shootings. All these characteristics make palm-vein a high security biometric feature. As a leading subject of biometrics technology, palm-vein image recognition has a wide prospect of application for its outstanding characters, such as high security. Palm vein image recognition has always been a research focus in recent years. This paper introduces the principle of palm-vein imaging first, then it provides a survey of the four stages for palm-vein image recognition: image acquisition, image preprocessing, feature extraction, and matching algorithms. According to different feature extraction approaches, we roughly group these algorithms into three categories: structure based, texture based, and subspace based methods. Finally, we conclude this paper describing the difficulty of palm-vein recognition technology and a discussion of future trends.关键词：pattern recognition;biometrics identification;palm vein image recognition;feature extraction4520|356|0更新时间：2024-05-07
- 摘要：Smoke detection with no latency for fire alarming is crucial to minimize fire damages and saving lives. Video as a spatio-temporal sensor covers a larger area than point sensors and it is sensitive to environment changes. Current smoke detection algorithms, however, are still difficult to achieve fast, accurate, and robust judgment on fire, even though they have used chromatic characters, texture, shape, flutter, flicker, spatial and temporal frequencies, as well as composite classifiers such as support vector machine, neural network, etc. This survey reviews the state-of-art of smoke detection methods and proposes three directions to achieve robust data processing. We argue that the success of visual smoke detection should be consolidated by a rigorous understanding of its physical characteristics, creation of a common test database for algorithm validation and comparison, and the establishment of a new criteria for the evaluation of algorithms.关键词：visual optics;smoke;fire;feature;chrominance;texture;shape;flutter;flicker;frequency;classifier3404|332|0更新时间：2024-05-07
- 摘要：The majority of methods based on fractional order differentiation for image enhancement always try to select different fractional orders and they fix the optimal one all the pixels in one image. However, these methods have difficulties in robustly enhancing images in complex environments. Therefore, a multi-bilateral filtering algorithm based on adaptive fractional order differentiation is proposed. The amplitude-frequency nonlinear joint model is established to adaptively select fractional order by analyzing the texture's characters, which can effectively overcome texture changes in images with complex environment. In the framework of bilateral filtering, introducing the guided image by adaptively selecting fractional order and detail transfer method makes sure that the texture details of an image are maintained/enhanced during denoising. Experiment results show that the proposed algorithm has better performance in computer vision and graphics, such as image filtering, dehazing and detail enhancement.关键词：image enhancement;texture detail enhancement;fractional order differentiation;bilateral filtering;edge preserving3141|360|0更新时间：2024-05-07
- 摘要：Compressed sensing theory samples and compresses the signals at the same time and uses the prior knowledge that signals can be represented sparsely in the transform domain to reconstruct the original signals with less measurements than Shannon-Nyquist theory. Recently, two-step Iterative Shrinkage/Threshold algorithm has been applied to compressed reconstruction as an optimization method to solve inverse problems for its tight connection with multi-scale geometry analysis, fewer parameters and simplicity. Using the hard and soft threshold operators in the time domain makes it hard to obtain sparse representation for two dimensional images. Consequently, the reconstruction precision of the algorithm is low. Based on the TwIST algorithm, an adaptive two-step Iterative Shrinkage/Threshold algorithm is presented. It makes use of the information obtained from current estimated values to calculate the step parameters and ensure the estimate value moving towards the optimum solution to improve its reconstruction precision. Regarding the poor ability to represent images sparsely, we use the Gaussian scale mixture model to model the curvelet neighborhood coefficients and enhance the ability of image sparse representation with the shift-invariance and directional-selectivity of the curvelet transform. Finally, the method is applied to image compression reconstruction and the experimental results show that it is better than both,the wavelet Gaussian scale mixture models and the curvelet hard threshold reconstruction methods in terms of subjective visual and peak signal noise ratio.关键词：compressed sensing;two-step iterative shrinkage/threshold algorithm;curvelet gaussian scale mixture;adaptive step2683|212|0更新时间：2024-05-07
- 摘要：Uniform block compressed sensing cannot separate the important region from the background for image signals effectively. A new notion of saliency-based adaptive block compressive sampling method is proposed. According to the saliency of the image signal, the quadtree algorithm is introduced to separate the important block and background block adaptively. The amount of observation samples is assigned dynamically to improve the quality of image reconstruction in salient regions. A high sampling rate is set for the important regions, while a low value is used for the background regions. Experimental results validate its rationality and effectiveness. Compared with uniform block compressed sensing, the proposed method needs fewer observations, and has a better performance in PSNR and MSSIM with a shorter running time.关键词：visual saliency;block compressive sampling;adaptive block;quadtree blgorithm3022|344|0更新时间：2024-05-07
- 摘要：In this paper, we show that for image zooming, the anisotropic partial differential equation is better than isotropic partial differential equation. Then we analyze the diffusion directions of the different fourth-order PDEs in this paper. While ensuring that the equation is anisotropic diffusion and in order to eliminate the block effects of low order partial differential equations in image processing, we construct two anisotropic fourth-order partial differential equations.From the data and quality of image zooming, we conclude that the models we present are better than the other four models.关键词：anisotropic diffusion;blocky affect;jagged effect;inverse diffusion2647|233|0更新时间：2024-05-07
- 摘要：In this paper, we propose a new color image segmentation approach based on the combined use of Voronoi tessellation and the (EM/MPM) algorithm. Voronoi tessellation is a well-established tool for the partition of a geometric region in stochastic geometry theory. Therefore, it is employed for partitioning the image domain into Voronoi polygons corresponding to the components of homogeneous regions that need to be segmented. The EM/MPM algorithm, which integrates the EM algorithm for parameter estimation with the MPM algorithm for segmentation, is also proposed to address color image segmentation. Quantitative experimental results on a synthetic color image show the performance of the proposed approach. Experiments have also been carried out on real world color images in order to validate the proposed approach.关键词：geometry tessellation;expectation maximization (EM);maximization of the posterior marginal (MPM);color image;segmentation2678|322|0更新时间：2024-05-07
- 摘要：In order to improve the performance of facial expression recognition by extracting the effective local features and global features, an algorithm for facial expression recognition based on adaptively weighted compound local binary pattern (AWCLBP) is proposed. First, the facial expression sub-regions are isolated by a preprocessing step. Then, the contribution maps(CM)of facial expression sub-regions are computed; Second, a compound local binary pattern(CLBP) extracts expression sub-regions and the global facial expression image and then cascade histograms are generated by connecting the histograms of the three features of the image and the one expression sub-regions that is weighted according to the CMs. Finally, the weighted cascade histograms are classified and recognized by using the chi-square distance and the nearest neighbor method. Experiment results on the facial expression database of JAFFE show that the proposed algorithm can be applied to achieve a higher recognition rate than other algorithms, such as, LBP, Gabor wavelet and the active appearance model.关键词：facial expression recognition;compound local binary pattern;adaptively weighted;Chi-square;nearest neighbor method3341|286|0更新时间：2024-05-07
- 摘要：The existing background modeling algorithms are in general quite sensitive to local illumination mutation in the scene. Therefore, a new temporal and spatial center-symmetric local binary pattern (TSCS-LBP) operator is proposed, and a background modeling algorithm based on the TSCS-LBP histogram is designed. The proposed operator extracts temporal information based on the center-symmetric local binary pattern (CS-LBP) operator. Considering the lighting environment, the pixel gray value itself has an important role. So the proposed operator includes the center pixel value information. Meanwhile, this operator uses the Niblack algorithm as the threshold of the local binary pattern. The threshold has an illumination factor, which can adjust adaptively according to the lighting situations in different regions. Owing to these techniques, the proposed operator can adapt to local illumination mutation quickly, while keeping a low computational complexity. The background modeling algorithm based on the proposed TSCS-LBP operator can detect foreground objects more accurately in the common experimental scene, and has higher noise immunity and testing accuracy. Meanwhile, the proposed algorithm has a good ability to adapt to scenes having local illumination mutation and it is better than existing algorithms. The experimental results prove the effectiveness and robustness of the proposed algorithm.关键词：local illumination mutation;adaptive threshold;illumination factor;temporal information;TSCS-LBP operator;background modeling2415|455|0更新时间：2024-05-07
- 摘要：A new object detection and tracking method is proposed based on generative and discriminative models. Firstl, stable features of object are extracted and represented by the DAISY feature descriptor, which has computational efficiency and is invariant to illumination, deformation, viewpoint, and scale. In this way, the object generative model is constructed. Second, the Hough forest classifier is adopted as discriminative model and the input patches of object are trained. Moreover, the discriminative codebook is updated by computing the similarity measurement between the detection results of the following video sequence and the codebook, and makes the codebook dynamic and adaptive. Experiment results show that the proposed algorithm, combining DAISY feature descriptor and Hough forest, has satisfactory tracking precision and good real-time performance, Additionally, it works well under the condition of partial occlusions and different image resolutions.关键词：object detection and tracking;generative model;discriminative model;DAISY feature descriptor;Hough forest3111|333|0更新时间：2024-05-07
- 摘要：Conventional vision based object detection or recognition models mostly depend on the view information of target examples. However, such attached view information is usually limited in several datasets. When the view information is scare, some generic object detection models try to learn the target by evaluating the view information with unsupervised learning methods. In this paper, a selective transfer learning method, TransferBoost, is improved and introduced to relieve the lack of object view information in training. The proposed TransferBoost, based on the GentleBoost framework, prompts the performance of learning the target by reusing prior knowledge from other object classes. Given a well labeled training set as source task, TransferBoost can transfer the knowledge on both instance level and task level by adjusting the weights of examples and task simultaneously. Such a combination of two levels transfers extracts useful information more effectively from mixed relevant source tasks and irrelevant source tasks. Our experimental results show, that compared to traditional machine learning methods, transfer learning needs much less training examples thus reduces the training cost of object detection or recognition models and extends the applicability of existing models.关键词：transfer learning;boosting;object recognition;object detection2306|256|0更新时间：2024-05-07
- 摘要：To reduce the sensitivity of the matching costs to complex optical distortions, such as vignetting, by fully exploiting the imaging model, a new matching cost using tensor analysis has been put forward. Compared with conventional costs, the proposed cost is resistive to complex distortions such as lens vignetting. Besides, it can reduce the matching ambiguity by reflecting the local image structure to a finer degree. We construct the proposed tensors rapidly on an integral image and measure their distance on the Riemannian manifold. In addition, a simple but effective disparity post-processing method is employed to further emend errors in the initial disparity map. Finally, the proposed method is compared with several other state-of-the-art disparity map generation methods under some challenging situations such as illumination variations and vignetting, the experimental results show that the proposed method is more robust and has higher disparity estimation accuracy.关键词：disparity;vignetting;tensor;matching cost2586|294|0更新时间：2024-05-07
- 摘要：Rotation invariance of existing binary local descriptors is achieved by constructing the descriptor relative to a dominant orientation, which is a major source of matching errors. A novel rotation-invariant binary local descriptor is proposed together with its matching method. Sampling points are equally spaced on circles concentric to the keypoint. The intensity comparison results of these sampling point pairs are concatenated into binary descriptor in a rotation-invariant ma- nner. By matching for all rotations, the descriptor is rotation-invariant. Combined with a multi-scale feature detector, scale invariance can also be achieved by sub-pixel sampling. Experimental results on standard evaluation datasets show that the proposed descriptor outperforms other state-of-the-art binary descriptors under rotation, scale or illumination transformation, as the error-prone dominant orientation calculation is avoided.关键词：image matching;local feature;binary descriptor;rotation invariance3287|231|0更新时间：2024-05-07
- 摘要：Traditional methods usually use corners and extreme points as feature points, and ignore the changes of texture so that the performances of the medical image classification are affected. A new feature point detection and description method is provided for medical image classification task using the Bag-of-Keypoints model. First, adaptive K-means is used to cluster images on the pixel-level, and the points where the clustering distribution in its univalue segment assimilating nucleus (USAN) changes rapidly are selected to be the features points. Second, the descriptor is defined in a polar coordinate system and a virtual dictionary is constructed in order to describe the image by virtual word histogram. Last, histogram intersection is used to measure the similarity between images, and K-nearest neighbor (KNN) is extended by it to finish the classification. Image retrieval in medical applications (IRMA)medical image classification code is strictly followed when experimental data is selected. The results show that the average value increased 4.5% than traditional classification; our method is more stable and robust for different classes of image, and meets the needs of clinical application better.关键词：image classification;feature point;Bag-of-Keypoints model;adaptive cluster;univalue segment assimilating nucleus (USAN)2455|322|0更新时间：2024-05-07
- 摘要：For accurate segmentation of abnormal nuclei in liquid-based cervical cell images, a new nuclei segmentation method is proposed, which uses adaptive and local strategies. The adaptive stage detects each nucleus region approximately by applying an efficient adaptive thresholding algorithm that uses intensity and texture information. The local stage refines each coarse segment within its local neighborhood by using a Poisson distribution based graph cuts, which utilizes boundary and region information. The proposed method is applied to Hematoxylin & Eosin stained liquid-based cervical cell images. The results show that the proposed method achieves a speed of 1.6 s per image, and significantly outperforms a state-of-the-art method by Li et al in 2012 in terms of nuclei detection rate and abnormal nuclei segmentation accuracy, both with a 19.7% improvement.关键词：liquid-based cervical cell;image;hematoxylin & eosin staining;abnormal nuclei;segmentation;adaptive local segmentation;graph cuts3175|359|0更新时间：2024-05-07
- 摘要：Optimal partitioning of spatial dataset is an import concern for many data management context such as spatial indexing, parallelizing GIS and distributed data access.This paper aims to discuss an adaptive spatial data partitioning method based on Hilbert space-filling curve and spatial pattern detection.A spatial data partitioning approach is proposed for spatial data partitioning of regular, random, and clustering objects, respectively.We show that the proposed method can achieve optimal partitioning point dataset without point dataset boundary information.We also show that the proposed method can adapt to available information about data distributions, data sizes and clustering.关键词：data partitioning;distribution pattern;Hilbert space-filling curve3103|314|0更新时间：2024-05-07
- 摘要：The intelligence of automated generalization developed slowly because of the integration of complex generalization technology, art, and cartographers' experience. Furthermore, the intelligent generalization based on machine-learning has also been one of the problems in the progress of automated generalization. A new approach of road network intelligent selection based on cases inductive reasoning is put forward in this paper, which takes the road network selection case lib of cartographers as leaning objects, the decision tree algorithm as reasoning machine, and concludes rules from expert case lib to form a decision tree. Then, the decision tree is transformed into rules that satisfy the computer's requirement. With these rules, computer could generalize road network selection automatically. Through this approach, the core problem of transforming cartographers' experience into rules that satisfying computer generalization automatically, and generalizing road network intelligently based on the rules is solved. Examples illustrate that, the new approach can conclude the core rules from the expert case lib and generalize map automatically, and the generalization results reflect the experts' experience of cartographic generalization effectively. Achieved generalization rules are suitable and usable to other special data of similar generalization conditions. Therefore, this method undertakes a new way for the intelligent automated generalization.关键词：road network;automated generalization case;decision tree;inductive reasoning;intelligence2641|328|0更新时间：2024-05-07
- 摘要：The Infrared target tracking system is a very important tracking system. In this paper, the detection process of the cross-shaped infrared point source tracking system is modeled through space mapping, signal sampling, and signal representation. With these models, this paper describes the simulation of the whole signal generation process. Two new features, the amplitude change rate and adaptive gate, are proposed for signal description. Combined with traditional characteristics of amplitude and time delay, this paper provides a status transfer framework for signal analysis and anti-jamming tracking. Furthermore, a complete 3D simulation platform is built to test the simulation model as well as the tracking algorithm and the result proves the validity of them.关键词：infrared point source;amplitude change rate;adaptive tracking gate;status transform3095|282|0更新时间：2024-05-07
- 摘要：Image segmentation is a fundamental step for SAR image based automatic target recognition (ATR). A method based on moment feature and multiple thresholds is proposed for moving and stationary target a cquisition and recognition (MSTAR) image segmentation. First, according to a comprehensive research of the statistics of MSTAR images, the mathematical description models for target regions, shadows, and background regions are constructed respectivedly. Then, the moment feature is defined, followed by the analysis of its basic properties. By transforming the image into moment feature space, the difference between target region and the other two types of regions is significantly enhanced. Finally, a strategy with multiple thresholds is constructed for the segmentation. The experiment results with MSTAR dataset indicate that the algorithm presented here has advantages not only on the noise robustness, but also on the segmentation effect, as well as the processing efficiency over the common-used methods, such as OTSU, fuzzy C-means(FCM), Markov random field(MRF), and constant false alarm rate (CFAR). Furthermore, this new method also performs well in the segmentation of MSTAR images with various scales and multiple targets.关键词：models for moving and stationary target a cquisition and recognition (MSTAR) image;image segmentation;moment feature analysis;multiple thresholds3162|473|0更新时间：2024-05-07
- 摘要：Polarimetric SAR data provide more information about objects' scattering properties and they have been widely used in the research of ship detection in the ocean.In this paper, an improved notch filter method is proposed, which uses both the polarimetric scattering mechanisms and the backscattering power of the target.By devising the projection subspace of the sea, azimuth ambiguities and coherent noises, a lower coherency of all those targets in the image can be reached, thus eliminating false alarms caused by them.What's more, a power related factor, the SPAN, is added to the detector in order to separate ships that have the similar scattering mechanism as the sea.The proposed method has been applied on RADARSAT-2 Fine Quad Mode data to validate its efficiency. Comparing to Polarimetric whitening filter(PWF) and SPAN method, the proposed method shows higher detection ability with low false alarms caused by azimuth ambiguities and coherent noises.关键词：ship;polarimetric SAR;Notch filter;false alarm;polarimetric scattering property2887|343|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