最新刊期
卷 6 ， 期 1 ， 2001
- 摘要：To summarize and promote the development of the new discipline——image engineering, a study for knowing and mastering the situation of related researchers is required. This paper, according to the principles and methods of bibliometrics, made a systematic investigation on the authors of articles published in 15 important journals in the last five years. All these journals are indexed in the survey series of“Image Engineering in China”. The statistics investigated include the number of authors, the author productivity, the number of collaborated publications, the average number of authors per paper, the active author group and the author variation ratio. Analysis and discussion on the statistics made are also presented. This work reveals the level, current status and alteration of researchers on image engineering, and provides useful information for summarizing the development, progress trends and application areas of image engineering in China.关键词：Image engineering;Bibliometrics;Statistics;Author analysis;Journal survey3093|382|0更新时间：2024-05-07
- 摘要：Remote sensing hyperspectral images provide more information than multispectral images in the sense that the spectral resolution of the former is much higher than that of the latter. They can solve the problems that the multispectral images can not. Their invention is a leap in the techniques of remote sensing for applications. There are two key subjects-classification and compression—for the researches of hyperspectral images now, which are both independent and dependent. Compression can be viewed as a kind of claasification realized by allocating different code words to different sub-blocks;on the contrary classification also can be considered as a type of compression extracting interesting object information. The main difference between them lies in the different standpoints eveluating the last results. Compression emphasizes the mean error of the reconstructed image, and classification emphasizes the misclassified probability of the images. Because of their inner relation, there are many similar realization algorithms. This paper first summarizes the methods of hyperspectral image classification and compression. Then the similar characteristics and differences for both are compared. Following two schemes for hyperspectral image classification and compression are introduced, and the computer simulations are carried out. Finally, the conclusions are given and the further research techniques are suggested.2651|459|0更新时间：2024-05-07
- 摘要：GIS(Geographical Information System) has been used more and more widely in various fields. One of the most important application is that GIS is integrated with OIS(Office Information System) to form the so called Office GIS. Data flow diagram and control flow diagram are two approaches used in traditional software engineering, but they are not well suited to Office GIS. Base on the integrated expression of control flow and data flow, a new approach is proposed in this paper, which integrates data flow and control flow considering both spatial and attribute data in Office GIS. The quality and efficiency of system design are greatly improved by applying the approach in system designing of Office GIS, which proves that the approach is feasible and effective.2573|440|0更新时间：2024-05-07
- 摘要：Symbol separation is a key step of the automatic input of topographic map. A great deal of important information can be acquired through the pick up of symbols. Although there has been a lot of algorithms aiming at this question, they were all obsessed by the conglutination problem. In this paper we define a new kind of morphological erosion operation and propose a new symbol separation algorithm based on it. Experiment result shows that this algorithm provides high resolution and rapid speed, and it can get over the familiar conglutination problem between symbols and lines that is inextricable to the general symbol separation algorithms. Its performance has met the requisition of actual automatic input system of topographical map. Further more, with a few modifications of the program, it can be extended to the recognition of other analogous line drawing such as engineering blueprint. We could also combine it with traditional algorithms to achieve better proformance.2656|443|0更新时间：2024-05-07
- 摘要：Low bit rate JPEG compressed images demonstrate serious blocking effect. Post processing is an effective way to reduce the artifact blocking effects. A post processing algorithm based on image wavelet extreme representation is studied in this paper. It is noted that in the wavelet domain, blocking effect can display the artifact wavelet transform modulus maxima at block boundaries. To take account of reducing blocking effects and maintaining original image edges, the maxima corresponding to block boundaries in the different region of image are processed in different ways. Experimental results show that the proposed method can significantly reduce blocking artifacts and improve PSNR and visual quality.2302|328|0更新时间：2024-05-07
- 摘要：It is more difficult to eliminate noise in color image than in gray image. In this paper, a method of color vector is described. Using this method, the noise in color image, which is made up of many monochromatic targets, can be restrained. Firstly, color vector is defined, and then the average of color vector is also defined. Secondly, a new analytical method of color vector is introduced. By calculating Euclidean distance between pixel, of which is analyzed, and averages of color vector of trained district, it is possible to segment rapidly the different monochromatic targets, which have been polluted. Thirdly, the images of monochromatic targets are smoothed separately. Finally, by combining the images of monochromatic targets that are processed and one of background, it is can eliminate noise in the color image greatly. The results of the method show that it is satisfy. The method is applicable to eliminate noise in image, which is made up of many monochromatic targets and complex background.2335|406|0更新时间：2024-05-07
- 摘要：Face object, is a special visual object defined in MPEG-4. Facial definition parameter(FDP) and facial animation parameter(FAP) are the sets of parameters to calibrate and animate the face object. The bitstream syntax for FDPs and FAPs in MPEG-4 are analyzed in this paper. The meaning of high level FAPs, viseme and expression, are explained with examples. All FAPs can be compressed with mask-based DPCM and/or DCT encoding. A rendering technology——displacement-controlling muscle model is proposed to reconstruct video sequences with natural facial expression from decoded FAPs and FDPs in MPEG-4 bitstream. There are two muscle models for different muscle stryles, parallel muscle and orbicular muscle. Different from traditional muscle models, which are controlled by intensity of muscle contraction, the proposed models are controlled by displacement of key-points affected by contraction of muscle. The reason behind this technology is that the visible displacement of key points is easier to be extracted from orighnal video sequence then the invisible muscle contraction. As an experiment result, reconstructed“Mona Lisa”with different expression is illustrated.2730|373|0更新时间：2024-05-07
- 摘要：For these characteristics of large landscape image such as huge saving memory and limited basic graph units to compose image, in this paper, a method based on multi level database was advanced to reduce the memory of large image. The database included two parts: graph database and mapping database. The organization mode of graph database and mapping database was presented, the mapping relation between graph units and geography position in image was put forward, the extraction of graph units from multi-level database was established. The mapping database was consisted with three level data table:the base function graph table, the function unit table, image table. The based function graph which was contructed by graph units, the function unit table which was recorded the relationship of the base function graphs described a part image, the image table was contented with all function graphs with variable situation. The reflection that established the relationship of two different data tables was described by palette, this reflection was unique. One point of high class level table reflected a unit of lower level table, by this way, it would be reduced the saving memory largely. This kind of multi level database had some characteristics such as high speed and accuracy locating, less memory of large image. By this way, 1G bytes image used memory less than 3M bytes.关键词：Image database;Multi level;Mapping database;CGI;Large image2486|455|0更新时间：2024-05-07
- 摘要：The soft threshold method proposed by Donoho is studied in this paper. The noise standard deviation of noise image and the thresholds of different scale are given. A separable 2 D wavelet filter is used so that the soft threshold denoising by Donoho is expediently applied to image processing, such as simultaneous denosing makes compression rate of a noisy image be large farthest. For noise image of nature scene and SAR, different image compression schemes are proposed respectively. Especially for SAR image, a natural logarithm transfors multiplicative noise to additive noise so that SAR image can be suppressed via the soft threshold denoising scheme. Experimental results show the decoded images by the soft threshold denoising have better quality than by the hard threshold denoising. It indicates that the improved ways in this paper are effective for noise image compression.2926|443|0更新时间：2024-05-07
- 摘要：Automatic fingerprint identification is one of the most significant biometrics technology. Preprocessing of fingerprint image play an important role in automatic fingerprint identification system(AFIS) and segmenting the ridges and valleys from fingerprint images is the basic task of preprocessing. This paper presents a new segment method for the ridges and valleys of fingerprint images. The ridges and valleys are considered as roof edge and their two sides are taken for step edges, then ridges and valleys can be located based on roof edge detection of multi scales B spline wavelet, and the area of the ridges and valleys is decided by the step edges. The valid scale range for roof target detection is discussed in detail, and we also give the simply and concretely segment method. The effectiveness of this algorithm has been testified for different quality fingerprints images. It must be point out that this segment method can be applied to detection of other similar roof targets.2365|430|0更新时间：2024-05-07
- 摘要：A novel method of reconstruction of order parameters in synergetic neural network is presented in this paper, Considering the neural network has the self learning ability, so we construct this linear transformantion using this ability. Additionally, considering the genetic algorithm has the globally optimal searching ability, so we can achieve these reconstruction parameters using genetic algorithm. The new method trained the synergetic neural network using genetic algorithm on the training samples set, after the convergence of genetic algorithm, the reconstruction parameters can be got. In the theory, genetic algorithm can achieve the globally optimal reconstruction parameters after infinite computation, which can be guaranteed by itself theory. So this method completely solves the construction of reconstruction parameters on the theory. The test on the samples from real applications shows:new method really can find a group of reconstruction parameters which improves the performance of synergetic neural network greatly.关键词：Order parameters;Reconstruction of order parameters;Synergetic neural networks;Synergetic computer;Genetic algorithm2216|390|0更新时间：2024-05-07
- 摘要：Multisensor data fusion has played an important role in image processing recently. For some images from the same scene, each of them has different noise because of their different sources. This paper presents a new kind of image data fusion algorithm based on the self organizing feature map neural network. This algorithm can be performed with three steps. In the first step,the pretreatment of the images is performed by the weighted median filter in order to remove some noise. In the second stage we use self organizing feature map neural network to cluster the pixels of each image and then extend hard partition into fuzzy partition. In the third stage, we fuse the data from the last step in conformity to a certain rule. The simulation results illustrate that this new algorithm can improve the quality of the image distinctly and the pretreatment of the images can improve the fusion result efficiently.1939|389|0更新时间：2024-05-07
- 摘要：Both picture quality and coder's outputting bit-rate are important in the video coding process. An adaptive video coding algorithm is proposed in this paper. The algorithm takes into account both picture quality and coder' s outputting bit-rate. It gives out a reasonable Bayes-cost function and introduces Bayes decision method into the video coding process. The algorithm uses Bayes decision method to choose coding strategy in order to agree with the statistical sort of image macroblock. The algorithm chooses the coding strategy whose Bayes-cost is the minimum and the subjective assessment of the coding strategy is the best. At the same time, the algorithm\ngives out the trade-off parameterλbetween picture quality and coder' s outputting bit-rate. The trade-off parameterλis updated according the state of the buffer and the coder's outputting bit-rate is smoothed in order to make the best use of the channel. This method can get better quality of reconstructed picture and higher average PSNR.2411|400|0更新时间：2024-05-07
- 摘要：How to improve the subjective visual quality of the video coded at low bit rate is an interested subject of many people. This paper proposes a video coding system based on object oriented bandwidth allocation(OOBA) technology to improve the subject quality of coded images. Exploiting human subjective visual characteristic sufficiently, this coder divides video sequence into multi video objects(VO) and allocates more bandwidth for the VO with more subjective significance to improve subjective quality of images coded at low bit rate. Each object is composed of macroblocks and coded separately. In bit stream context, the OOBA coder is compatible with H.263. For reasonable bandwidth allocation, present three schemes to allocate bandwidth for multi objects: rate distortion(R D) model based scheme ,sequence analysis based scheme and ratio weighting scheme. The result of experiments shows that the PSNR of OOBA coder is a little lower than that of frame based coder, but the subjective quality is much better. So, it proves the OOBA coder effective and indicates it is not enough to evaluate a video coder only with objective criterion such as PSNR.2426|365|0更新时间：2024-05-07
- 摘要：The methods of time frequency analysis include linear, quadratic and adaptive methods. They provide effective tools for analyzing signal time varying spectrum in time frequency plane. Each of them possesses its special advantages as well as disadvantages. Therefore, in practical applications, to make a balance in time and frequency resolution and to reduce cross term interference, different methods should be employed to deal with different kinds of signals in terms of the signals' previous knowledge. In this paper, we analyzed some typical signal models via using different time frequency analysis methods and found some effective methods that are suitable for these models. For examples, adaptive method is suitable for analyzing Gaussian like or frequency hopping signals, but STFT or WVD is suitable for chirp like signals. We also discussed the applications of these methods on image analysis and processing.关键词：Time frequency analysis;Signal;Time frequency resolution;Cross term interference3335|422|0更新时间：2024-05-07
- 摘要：The neural network models based on adaptive resonance theory(ART) are capable of organizing stable recognition categories for arbitrary binary or real imput patterns. However the ART neural networks are not sensitive to the distinguishing of those categories which there are only a few components in obvious difference between them. A new ART2 neural network model with more vigorous vigilance test criterion is proposed in this paper. The modified intercepted hyperbola function is adopted in the new vigilance test criterion to calculate the matching degree between the input vector and the weight vector of top to bottom. On one hand, the hyperbola function reduces the effect of noises and on the other hand, it emphasizes the effect of those components of input vector which have impulsive differences to the corresponding components of weight vector. The palm image recognition using the ART neural networks with the new vigilance test criterion has been carried out in this paper, the experiment results shows that the new vigilance test criterion is more robust to noises, and the new ART2 neural network can gain higher recognition rate under lower SNR.关键词：pattern recognition;neural networks;ART2;Vigilance test2532|369|0更新时间：2024-05-07
- 摘要：As a new rendering thcnique, image based rendering(IBR) receives more and more attention becarse of its high efficiency in virtual scenes modeling and rendering comparing with traditional geometry based rendering. The major challenge of IBR is to represent the continuous scene with images of discontinuous views, so that users can change their viewpoints arbitrarily in real time. In other words, we should find a way to stitch images of different views together. In this paper, we show the implementation of an image based spherical virtual in door environment. The scene is represented as a spherical panorama, which means user is fixed at the center of the sphere and can only look around. Compared with previous works, our system can stitch a continuous panorama from several photos with a semiautomatic method more easily. Meanwhile, a lookup table based algorithm is used to realize the real time walkthrough on a fixed point. At the end of this paper, some experimental results can demonstrate the efficiency and quality of our method.关键词：Image based rendering;panorama;Image warping;Image stitching;Walkthrough2834|529|0更新时间：2024-05-07
- 摘要：Edge detection is an important part of image processing. This paper makes some improvement to the Pal.King fuzzy edge detection algorithm and brings forward a fast fuzzy edge detection algorithm. The fast algorithm not only simplifies the complex G and G -1 calculation in Pal.King algorithm, but also determines the optimal threshold value of degree of dependence of transformation by experiments, and reduces the iteration times. Finally, two group of experiments are put forward, and it can be seen by comparison that the fast algorithm not only improves the Pal.King algorithm efficiency, but also obtains preferable detection effects comparing to the Pal.King algorithm. In addition, it can be seen from the result of the experiments that the fast algorithm not only is applicable for general images, but also is the same with the remote sense images, and the fast algorithm has powerful ability in detection fuzzy edge and exiguous edge. The fast algorithm has superiority capability, and it is a promising and applied image processing algorithm.4403|470|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