最新刊期
卷 10 ， 期 4 ， 2005
- 摘要：As a promising means to ascertain the copyright infringement of digital media, digital watermarking technique is getting more and more mature and new algorithms have been emerging. In the meantime, more and more attacks are confronting with it. This paper discusses desynchronization attack in detail, which disables the correlator through geometrical distortions and is very difficult to tackle. It mainly comprises global affine transformation attack and local random bending attack. Many algorithms can well withstand the former, but the latter almost defeats all existing algorithms. We categorize and summarize the countermeasures in detail, and analyze their deficiencies respectively. Finally we point out that how to effectively cope with desynchronization attack is still an open question and deserves a thorough research.3463|229|0更新时间：2024-05-07
-
- 摘要：The amount of remotely data images increases rapidly, and the information that the images contain becomes more and more complicated. How to classify remotely sensed images automatically and effectively is a problem needed to be solved. This paper explores the application of Fuzzy ARTMAP neural network in classification of land cover. The adjusting methods of vigilance parameter are summarized. An automatic adjusting algorithm is proposed. The simulation results show that the automatic adjustment algorithm can increase the efficiency of selecting the optimum parameter value. The convergence speed and classification accuracy can also be improved through the automatic adjusting algorithm. The Fuzzy ARTMAP neural network with the automatic adjusting algorithm has shorter training time and higher classification accuracy than maximum likelihood classifier and traditional Fuzzy ARTMAP. A relatively satisfied classification result can be achieved by using Fuzzy ARTMAP in land cover classification.3003|233|0更新时间：2024-05-07
-
-
-
- 摘要：Super-resolution image reconstruction has been one of the most active research areas in recent years. In this paper, a super-resolution solution is proposed to the problem of obtaining a high resolution image from several low resolution images that have been subsampled and displaced by different amounts of sub-pixel shifts. The method is based on the regularization technique, solving the constrained optimization by proposed iteration steps. At each iteration step, the regularization parameter is determined using the partially reconstructed image solved at the last step. The proposed algorithm is tested on synthetic images,and the reconstructed images are evaluated by a PSNR method. The results indicate that the proposed algorithm has considerable effectiveness in terms of both objective measurements and visual evaluation.3084|193|0更新时间：2024-05-07
- 摘要：A computational framework for the temporal-spatial alignment of multi-sensor image sequences is presented in this paper. The framework is suitable to the circumstance where the cameras are static; the captured sequences contain moving objects but the initial segments of the sequences are frames of the static background. The framework first registers the static backgrounds of the sequences to yield the initial spatial transformation. Then it uses the correspondence of the centroids of moving objects to estimate the initial temporal transformation. Finally, mutual information is incorporated into this framework to compute the final temporal-spatial transformations. This framework, which can obtain a sub-pixel and sub-frame registration accuracy, has been successfully applied to a visible/infrared sequence alignment experiment.2798|166|0更新时间：2024-05-07
- 摘要：In reverse analysis of integrated circuits, three components of a color IC line-net image are often needed to be fused to a gray one to reduce complexity. Due to the local similarity in IC images, fusion is only performed in an automatically selected local neighborhood to get the global optimal weights in this paper. A new line model is constructed to describe the feature of interest and the model based fusion is divided into feature extraction, feature enhancement and noise suppression. Experiments show the superiority of local line model based fusion algorithm over traditional methods in enhancing the feature of interest and the quality of the fused image.2536|217|0更新时间：2024-05-07
- 摘要：Text in video can provide an important supplemental source of index semantic information. In this paper, an algorithm of automatic video text locating, tracking and recognition is presented. First, the text regions are located by several steps: wavelet decomposition, high frequency component intensity and density detection, horizontal and vertical convex detection based LH, and text locating. Then the text regions are tracked in next consecutive frames. After multiple frames averaging, the text regions are enhanced. By binarization of the enhanced text regions followed by component analysis, the text regions with clean background are obtained. Then the text regions are recognized by OCR software, the final text strings are attained. Experimental results show that the proposed algorithm can detect and track text region simply and effectively.3174|198|0更新时间：2024-05-07
- 摘要：In this paper, taking building detection and recognition as an instance, by using improved Hough transform, several line analysis strategies and measures to remove the inveracious targets are presented. The experimental results show that the approach with these methods can get acceptable results when image processing with scaling, different angles of view , various conditions of sunlight and mosaic phenomenon involved.2763|182|0更新时间：2024-05-07
- 摘要：A number of current face recognition algorithms use whole face representations found by statistical methods. Independent Component Analysis(ICA) is an example of such methods which is based on signal high-order statistic characteristics. While such unavoidable external factors as illumination, posture and information deformity will cause great changes of gray-scale image data, and eventually will decrease the stability of recognition. This paper presents a local face recognition algorithm that is based on ICA and the nearest feature line (NFL). Firstly, by using manually aligned eye position, segmenting a face image into two parts according to the geometric characteristics of human face, removing hair style and other useless information, then processing principal component analysis (PCA) and ICA for respective parts, and calculating corresponding NFL distance, ultimately processing comprehensive recognition by setting reasonable coefficient of weight. Compared with traditional holistic image representation, this method has many advantages, such as a much higher recognition rate, more stable and flexible in practice. Through a number of experiments, it proves to be an efficient human face recognition algorithm.2646|189|0更新时间：2024-05-07
- 摘要：In this paper, Multi-Scale two-dimensional wavelet transform is imported to analysze fabric surface wrinkle in order to acquire the finer image information. Firstly, fabric image can be filtered through Gaussian filter, and decomposed by wavelet transform; meanwhile, high frequency information is extracted. Secondly, four kinds of wrinkle feature parameter are applied to calculate the fabric wrinkle degree with different wrinkle replica, which are horizontal variance, vertical variance, horizontal offset and vertical offset separately. Through analyzing the correlation coefficient between feature parameter and wrinkle grade, which indicates the four kinds of wrinkle feature parameter can be taken as the input value for pattern recognition. Finally, Kohonen self-organized neural network is also used to evaluate fabric wrinkle grade objectively. The wrinkle feature parameters are input to the Kohonen self-organized neural network, through training and studying process, the output value can be obtained, different wrinkle grade of fabric replica will be classified by applying self-organized neural network, and wrinkle grade of 26 different type fabrics can be evaluated according to this result. For describing the assessment result with quantify, the correlation coefficient is calculated between objective assessment and subjective assessment in order to validate the feasibility of this method.2382|190|0更新时间：2024-05-07
- 摘要：Considering the problem of detecting artifacts in underwater images, a fractal-based algorithm is proposed in this paper. Because the fractal model differs greatly from man-made objects but perfectly approximates the natural objects, so the algorithm based on fractal models could accurately distinguish the artifacts from natural backgrounds. The definitions and calculations of fractal dimension are discussed in this paper. The underwater images are registered as artifacts regions and non-artifacts regions by thresholding based on the fractal features. This fractal-based object detection is applied to some noisy underwater images and the corresponding detection results are presented in this paper. The experimental results indicated that the fractal features are fit for the classification of artifacts and natural backgrounds, and have somewhat low sensitivity to the Gaussian noise. So the fractal-based algorithm is appropriate to detecting the artifacts in underwater images that are often contaminated.2851|178|0更新时间：2024-05-07
- 摘要：As a classical image segmentation method, Otsu adaptive threshold algorithm has applied widely in image processing. The application of the two-dimensional Otsu threshold algorithm based on the Otsu threshold algorithm has been restricted for the long-paying computation. This paper gives a fast algorithm for two-dimensional Otsu adaptive threshold algorithm that overcomes the disadvantage of high computational complexity. The fast algorithm changes the two-dimensional threshold to one-dimensional threshold by using new area partition method, and enhances the computational speed of the two-dimensional Otsu algorithm. The experimental result has demonstrated that the computational time of the fast method is far less than that of the source two-dimensional one.4661|211|0更新时间：2024-05-07
- 摘要：This paper is devoted itself to segmentation of texture images. Based on the theory of total variation minimization and the active contour image segmentation method, we proposed a simple linear model of texture images which regards a texture image as a sum of a photo prototype image and a texture sub-image. Using the total variation minimization method the simplified prototype image can be extracted from the origin image. A coarse border can be located by segmenting this simplified image. Based on the coarse border, a higher accuracy result can be obtained by taking the original image into account. We choose the geometric MDL active contour for image segmentation and applied AOS scheme for the numerical solution of the nonlinear diffusion equation of the total variation minimization. Our method is unsupervised. Experiments on both synthetic and natural texture images show that the method is effective.3939|230|0更新时间：2024-05-07
- 摘要：This paper presents a new method of digital watermarking of 2D vector graphics to protect its authority. The watermark is embedded in the complex wavelet domain of relative coordinates line. Robustness to some common manipulations, such as translation, rotation scaling and local modification, have been proved by preliminary experimental results.3071|200|0更新时间：2024-05-07
- 摘要：The first linear principal component is the optimal linear 1-d summarization of the data. Principal curves are nonlinear generalizations of the first linear principal component. Principal component analysis is a linear method, but the most data are nonlinear. Sometimes the linear principal component analysis works inadequately when the data are nonlinear. In this paper, a new nonlinear analytic method, principal curve component analysis (PC~2A) is proposed. This method can model nonlinear data effectively, which analyzes the data from its inherence and emphasizes the non-parametric characteristic. And the method uses the advanced neural network to model data. This is an excellent approach for expressing the nonlinear relationship because of its universal approximation property. Experimental results show that principal curve component analysis is excellent for solving nonlinear principal component problem, and it has great applications potentials.4388|187|0更新时间：2024-05-07
-
- 关键词：DCT domain;quasi-convoluted down-sampling;fast algorithm;peak signal to noise ratio3216|227|0更新时间：2024-05-07
- 摘要：The shape-preserving quadratic spline interpolations introduced by Schumaker need users to adjust the slopes to satisfy monotone condition, We study carefully the reasons of requiring users to adjust the slopes and introduce a new method that does not need the users to adjust the slopes. The new method first finds out the intervals that do not satisfy monotone conditions, then chooses additional split points that are given suitable slopes to satisfying monotone conditions, at last constructs shape preserving polynomial interpolation based on the method of Schumaker. Examples are given to illustrate the efficiency of the interpolation.3043|175|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