最新刊期
卷 18 ， 期 6 ， 2013
- 摘要：Blind digital image forensics, a technology for detecting image authenticity and integrity without relying on any pre-embedded information, is emerging as a new hotspot in the digital media security filed. Since JPEG is the most popular image format and blocking artifacts are the inherent characteristics of JPEG images, using blocking artifacts more effectively for the authentication of JPEG image forgeries has very important practical significance and application value. First, the state-of-the-art algorithms of blind forensics based on JPEG image coding characteristics are classified and analyzed. Then we focus on blind forensic algorithms of tempered JPEG images based on blocking artifacts. Two types are introduced and summarized in detail: one based on blocking artifacts measurement and the other based on blocking artifacts grid extraction. Finally, we discuss unresolved problems and future research directions.关键词：JPEG blocking artifacts;image forgery;passive-blind forensics;tampering detection3111|254|0更新时间：2024-05-07
- 摘要：The PMD(photonic mixer device) camera is a three-dimensional imaging device based on TOF(time-of-flight), which is able to obtain high-precision distance information with two-dimensional gray-scale images. However, it has some disadvantages, such as low horizontal resolution, big random noise, etc. In this paper, we fuse the PMD distance information and a high-resolution RGB image, proposing a new kind of data fusion method based on texture projection and bicubic interpolation with credibility. This method fully considers the relation between signal amplitude of the PMD camera and the credibility of the distance information, strengthening the influence of the fusion result by the precise distance information. Furthermore it has provided the reconstruction of PMD images in a world coordinate system through distance information, reducing the computational complexity. The experimental results show that this approach obtains high-resolution images with color information and distance information. The distance information of the fused image is more accurate and rich, and it has reduced the impact of random noise, and the run-time is less.关键词：data fusion;bicubic interpolation;credibility;PMD (photonic mixer device) camera3240|801|0更新时间：2024-05-07
- 摘要：The fractional calculus is used in edge detection much more frequently due to its good performance in strengthening details, Among those studies, most are made in RGB color space. However, the brightness information and the chrominance information are related to each other in RGB color space. This defect prevents us from obtaining both the brightness edge and the chrominance edge simultaneously. Therefore, using fractional calculus in other color spaces whose brightness information and chrominance information are separated, is significant in theory and practice. In this paper, to make the most use of both brightness and color information, we propose a novel edge detection method by using fractional differentiation in CIE Lab color space for edge detection. Compared with detecting edges directly in the RGB color space, the edge extracted by the proposed method is much more consistent with human visual preception. Furthermore, the continuity and the anti-disturbance are better too. By contrast to other classical algorithms, the proposed method also has significant advantage.关键词：fractional calculus;edge detection;RGB color space;CIE L;a;b;color space;Otsu2855|328|0更新时间：2024-05-07
- 摘要：In order to improve the detection quality of direction of the objects moving in fixed direction from blurred image, In this paper, we propose a new algorithm for detection of moving direction, which is based on the pre-processing of spectrum image. First, the spectrum image of motion-blur image is transformed twice with Fourier logarithmic to meet refinment of bright lines. Second, with the previous spectrum as input, the image is bi-value processing with slipping neighbour operation, eliminating image noise and cross bright line. Finally, the pre-processed image is performed with Radon transform, detecting image linear characteristic, and mapping the detection results into direction of the blurred image. The experimental results show as below: 1) in different fuzzy scale and direction of the environment, the proposed algorithm can always limit the movement direction detection error under 0.5°;2) our algorithm can obtain better movement direction detection than other related algorithms.关键词：spectrum analysis;detection of motion direction;high brightness fringe refinement;cross bright line3019|334|0更新时间：2024-05-07
- 摘要：For a long time, forest fire detection is one of the most important research areas all over the world. It is crucial for protecting the earth and human survival. Real-time and accuracy is the essential need in surveillance system, especially in forest fire detection. However, the traditional sensor-based and conventional image-based fire detection approaches can not satisfy the needs. To achieve an effective detection of such fire, an image-based forest fire detection algorithm based on dynamic texture analysis is proposed. The first step is to establish Linear Dynamic System(LDS)model on the video image sequences captured by CCD camera, then analysis the dynamic textures, and finally determine the existence of the fire by Adaboost classifier. Experimental results demonstrate that the rate of accuracy of the proposed algorithm can achieve 95%. It is efficient and robust with good application prospects.关键词：forest fire detection;dynamic texture;linear dynamic system;martin distance;Adaboost2927|290|0更新时间：2024-05-07
- 摘要：In order to solve the problems of traditional X-ray image mosaic methods, such as the demand for fixed signs, poor robustness, and artifacts in panoramic images,we propose an automatic rotation-independent image mosaic method. This method is based on feature point registration and an improved correlation which is invariant to rotation. It needs lower overlapping areas among images. Two-dimensional dynamic weight and balance exposure have been adopted in image-fusion. Our experiments show that the registration algorithm can improve the accuracy of the results as well as the robustness, and the fusion algorithm can effectively balance the exposure difference and eliminate the mosaic artifacts, greatly improving the quality of the panoramic images.关键词：image registration;image fusion;image mosaic;image correlation;X-ray image2872|290|0更新时间：2024-05-07
- 摘要：In the myocardial perfusion image, the location and shape of the heart changes with respiration and heartbeat. Meanwhile, the image intensity also changes as the contrast agent flowing in the heart chambers. It is difficult to apply the traditional registration methods, such as cross correlation and mutual information to the registration of myocardial perfusion images. In this paper, we introduce Markov random fields(MRF)to tackle this problem. In the Markov energy function, the image block is normalized to get rid of the intensity change effect. In order to remove the accumulated error, which is common in registration of image series, a pseudo ground-truth image is calculated as template for each of the myocardial perfusion images. The accumulated error can be removed by warping each myocardial perfusion image to its corresponding pseudo ground-truth image. Experimental results demonstrate that our method can effectively correct the displacement and deformation of the myocardial perfusion image.关键词：myocardial perfusion MR image;non-rigid registration;pseudo ground-truth;Markov random field;normalization2573|242|0更新时间：2024-05-07
- 摘要：Compared with general scene images, unmanned aerial vehicle(UAV)images provide richer texture information, and often there are more serious problems for the one-to-many correspondence between local features and target objects. The traditional speeded-up robust features (SURF) algorithm would be inapplicable to UAV images. Therefore, an improved spatially constrained SURF method is proposed for UAV image matching and mosaicking. In the first feature point matching phase, SURF feature points are extracted from the whole base image and the blocks of the target image, respectively, a cosine-based spatial constraint relationship is built using the selected two pairs of points and imposed on the feature point dual matching process between the central block in the target image and the base image. In the second phase, the initial parameters of geometric transformation are calculated using the feature point points obtained in the first phase and used to estimate locations in the base image corresponding to points in the target image. For each feature point in the target image, point matching just need to be done within the neighborhood of the estimated locations so as to ensure matching efficiency and reliability. Meanwhile, uniformly distributed feature points are achieved with the constraint of point intensity. Finally, the obtained feature points are used for UAV image registration and mosaicking. The performance is compared with the manually selected points that are uniformly distributed. Experimental results illustrate the validity of the presented method.关键词：SURF feature points;spatial constraint;unmaned aerial vehicle image;image mosaic;image blocking3554|259|0更新时间：2024-05-07
- 摘要：River detection in high resolution remote sensing images is one of the most popular topics of research in computer vision. In this paper, a novel river detection algorithm in high-resolution remote sensing images by using support vector machine(SVM)and level set is proposed. According to the characteristic of the river, we employ texture feature and benchmark information diffusion feature as the feature vectors to train the support vector machine classifiers in order to perform the coarse segmentation of rivers. Then the distance regularized level set evolution(DRLSE) model, which takes the results of the coarse segmentation as the initial curves, is used to capture the desirable shapes of the rivers. Experiments are executed on IKONOS 1m-resolution images and the results demonstrate the superior performance of the proposed algorithm in terms of accuracy, efficiency, and robustness.关键词：support vector machine;level set;benchmark information diffusion;river detection3006|339|0更新时间：2024-05-07
- 摘要：As used in scale transformation for changing spatial features, incremental generalization technology is one of the main aspects of the multi-scale data propagating updating process. After analyzing the domestic and international research, an incremental generalization algorithm based on gradually expanding the influencing domain is proposed, which consists of the following steps: first, the processed area is divided into parts using hierarchy technique; second, the changed feature and it surroundings that are influencing the features are detected, so as to generalize both of them with correct generalization operations according to the area characteristics; third, expanding the influencing domain of the generalized features so as to detect new corresponding features, and stopping the circles until no influencing feature is detected. Examples illustrate that the method described in this paper is more effective for scale transformation and updating large scale maps.关键词：influencing domain;expanding;incremental;map generalization;multi-scale;updating2795|219|0更新时间：2024-05-07
- 摘要：A scene change detection algorithm based on non-connected points is proposed to solve the problems of scene changes existed in videos, which can improve the coding performance. The complexity of the proposed algorithm is low and scene change detection is processing at the same time of the motion estimation. Scene changes can cause different GOP(group of pictures)sizes, which can result in GOP with a short size. We propose an improved adaptive GOP motion compensation temporal filtering, which can effectively avoid the short GOP problem resulting in a decline of coding perfor- mance. For each GOP generated by scene change detection, a frame-layer rate control algorithm based on a rate distortion model is proposed, using the relation between the distortion and the rate and the complexity of the video frame to optimize the rate distribution, aiming at improving the quality of the reconstructed video. The experimental results show that the proposed algorithm can achieve better performance than other rate control algorithms.关键词：non connected point;scene change;adaptive;rate distortion model;rate control4978|224|0更新时间：2024-05-07
- 摘要：To solve the contradiction between the enormous amount of medical image data and the limited storage space and transfer bandwidth, we propose a near-lossless compression algorithm for medical images in PACS(picture archiving and communication system). First, the lesion area and background are transformed into the shearlet domain and wavelet domain respectivel. Second, we select the significant coefficients that can approximate the lesion area accurately for denoising and preliminary compression. Third, we make lossless Huffman coding to the significant coefficients selected by the previous step and process the wavelet coefficients of the background by quantization and SPIHT coding. Finally, we use two result images processed by decoding and inverse transform and obtain the complete reconstructed image. Experiment results show that the MSSIM and PSNR between the original lesion area and the reconstructed image obtained by the new algorithm increased by 6% and 154% respectively compared to the wavelet-based method with the same compression ratio, for the whole image, the MSSIM and PSNR increased by 2% and 13% respectively.关键词：medical image compression;wavelet transform;shearlet transform;huffman coding4151|265|0更新时间：2024-05-07
- 摘要：Visual word generation is a key observation in obtaining the bag-of-visual-words (BOVW)representation for image retrieval: query image features are mapped to their visual words according to the pre-clustered codebook. In this paper, we propose a novel generation approach based on the spatial correlation of visual words. A visual word co-occurrence table is constructed in the first step. Given the known visual words, a new probabilistic predictor is then presented to acce- lerate the generation of their neighboring visual words. We combine the co-occurrence table with the fast library for approximate nearest neighbors (FLANN), and test it on the Oxford dataset. Comparisons with representative approaches suggest the efficiency and effectiveness of the new scheme.关键词：bag-of-visual-words (BOVW);spatial correlation;visual word co-occurrence table;probabilistic predictor4296|267|0更新时间：2024-05-07
- 摘要：In non-overlapping multi-camera surveillance systems person re-identification is one of the main issues. Aiming for person re-identification useing statistical properties of the objects and features by training, we propose a method by combining global and local features to identify the same person in different images. This method does not need a training phase, and it is robust to different viewpoints, illumination changes, and varying poses. First, the object is recognized roughly by spatiograms. Then the human target is divided into three parts. By ignoring the head part, the local color and shape features of the main body, the arms and the legs are extracted. Thus, the recognition of the person is carried out according to the Earth movers distance of the local features. The experimental results show that the proposed method has a higher accuracy rate, and it is invariant to the effects of occlusion and background adhesion.关键词：non-overlapping multi-cameras;person re-identification;spatiograms;local features5423|318|0更新时间：2024-05-07
- 摘要：We extend the construction of a G continuous curve based on a guiding polyline from the parametric form to the quadric and cubic algebraic spline form to avoid obstacles. First, a series of control polygons are obtained by adding the midpoints of guiding polylines except for the first and last line segments. Then, based on the control polygons and the corres- ponding obstacles, the shape parameter(s)of the whole algebraic spline curve, which avoids every obstacle, can be obtained. The new spline curve not only determines the position relation between the curve and the given point, but also shows its advantages directly, such as low degree, G continuity, simple calculation, shape-preserving, and adjustment by the control polygon. All shape parameters in the cubic algebraic spline were local, which enhances the flexibility of the geometric design.关键词：geometric design;algebraic spline curve;G;continuity;avoid obstacles4324|240|0更新时间：2024-05-07
- 摘要：Focusing on the complex data structure of digital elevation model (DEM) and the poor rendering speed in real terrain visualization, we propose a fast rendering method based on adaptive multi-feature fusion for realistic terrains. To introduce the entropy of terrain elevation, real DEM elevation data can be extracted for generating an overall framework. According to the random midpoint displacement fractal algorithm and optimized fractal parameters, the high frequency detail can be increased. To calculate the distance threshold between the viewpoint and the terrain, this corresponds to the level of details (LOD), so that it can achieve adaptive scheduling. Additionally, by using the uncertainty determinant factor, the characteristics of the terrain profile can be updated. Finally, the algorithm is carried out using parallel processing, taking full advantage of the graphic processing unit (GPU) for accelerating the terrain rendering. The experimental results show that the generated terrain has higher fidelity and better real-time capabilily.关键词：adaptive;multiple features fusion;fractal terrain;fast rendering;level of details (LOD)4400|280|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