最新刊期
卷 15 ， 期 5 ， 2010
- 摘要：This is the fifteenth annual bibliographies in the survey series 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, 1008 references on image engineering research and technique are selected carefully from 3604 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. 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 last year). 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 2009, it should be pointed out particularly that, in 2009 the number of research papers for image engineering, published in the above 15 journals still maintains an increase and attends a new high stage in the history. A strong tendency of continuing development of image engineering in China is clearly visible. In addition, taking the opportunity of 15th year of survey, some further statistics and analyses on the selections of publications and numbers of publications in all categories are provided on the basis of dividing the 15 years into three “five-year” separately. Thus, the readers could obtain even more complete and reliable information than before.关键词：image engineering;image processing;image analysis;image understanding;technique application;literature survey;literature statistics;literature classification3945|479|0更新时间：2024-05-07
- 摘要：Image smoothing algorithms based on PDE and variational formulation minimization can denoise effectively while preserving the edge information, but the texture information can not be kept as the noise and texture are difficult to discriminate. A new texture preserving filter is proposed. The new algorithm first uses image decomposition model to separate image into the geometry part and the noise/texture part, then calculates the local variance of the latter which is incorporated with the traditional deviation cost to form a spatially adaptive constraint. The new filter smoothes less in the texture regions, thus could preserve the texture information. The visual effect and data analysis of the experiment result proves the effectiveness of the algorithm.3983|413|0更新时间：2024-05-07
- 摘要：To deal with the error segmentation problem of the existing video algorithms under complex and dynamic scenes, the proposed method extracts spatial-temporal attention features with salient maps, and adopts hierarchical conditional random field for video segmentation. Firstly, the algorithm constructs a weighted combination model based on spatial-temporal features by using information theory. Then, it uses the defined model to compute probability distribution of salient maps, which can locate region of moving object effectively. Finally, the Gaussian mixture model is adopted to construct energy functions with the above probability distribution, and the hierarchical conditional random field is used to constraint these feature energy functions to refine final segmentation. The experiment results showed that the algorithm can avoid the error segmentation problem induced by camera movement. So it is robust to handle the videos under complex and dynamic scenes.关键词：video segmentation;spatial-temporal attention model;hierarchical conditional random field4838|308|0更新时间：2024-05-07
- 摘要：Research on CAD based boundary-feature descriptions of skin lesions for early diagnosis and medical treatments are crucial as boundary irregularity of melanomas is one of the most important clinical indicators to discriminate lesiens from other benign moles. Conventional fractal dimension（FD） is utilized to describe boundary complexity based on self-similarity measures. The criminative power of FDs is low due to its global property and lack of detail information. The objective of the paper is to explore new irregularity descriptors of object boundaries at different scales. In the paper, there are two novel measures: the irregularities of boundary structures and multi-scale features related to boundary roughness are described using an integrated quantitative model combining Gaussian filtering and local FDs. The advantage of the latter approach is that feature clusters of boundary irregularity are formed at different scales in the image space, so that the extracted measurements from multi-scale descriptions and different viewpoints（statistics and boundary-like roughness） can provide effective descriptors compared to the conventional FD and other boundary based methods and will be helpful for further classification tasks. Experiments show that the proposed irregular descriptors not only enhance fine expressions of boundary complexity but also can effectively discriminate melanomas among moles using statistical features of the boundary roughness at different scales.关键词：melanomas;boundary irregularity;multiscale local fractal dimension3236|268|0更新时间：2024-05-07
- 摘要：The scene recognition between indoor and outdoor is one of the basic problems in image processing. A solution to this problem which does not require image segmentation and object recognition is proposed in this paper. First of all, a 5-level wavelet transform was implemented on the image, then the rotation invariant LBP algorithm was used to extract the texture feature from 2-level to 5-level LL sub-images. Afterwards, the mean and variance of the LH, HL, HH sub-images from 2-level to 1-level were computed. Finally, these two low-dimensional eigenvectors were concatenated as the image feature to classify the indoor and outdoor scene images. The experiment results indicate that our algorithm performs well on indoor/outdoor classification, and the overall texture information of the fuzzy image is only needed in the scene recognition between indoor and outdoor, rather than the local detailed information such as object shape.关键词：indoor-outdoor scene recognition;rotation invariant;LBP;wavelet transform;texture feature4353|304|0更新时间：2024-05-07
- 摘要：Priori embedding for character segmentation in license plate recognition(LPR) is difficult, and the segmentation results greatly depended on the precision of license localization. Thus in this paper, we present a novel integration method of the prior knowledge and its corresponding character segmentation algorithm. Given one category, the segmentation procedure can be transformed to a set of Markov transitions where the state is defined by the characters permutation. With the combination of connected-component-based and vertical-projection-based algorithms, the optimized segmentation result and its confidence level can be obtained. One advantage of our method is that only coarse localization is enough for the segmentation algorithm. The proposed method is uniform for different license categories, which reduces the coding complexity. The performance improvement of the proposed approach is illustrated by the LPR systems applied practically in China and Malaysia, both contains multiple categories of license plates.关键词：priori embedding;license character segmentation;Markov chains3497|318|0更新时间：2024-05-07
- 摘要：The region based segmentation method has been attracting much attention in automatic or semi-automatic image segmentation research. This paper proposes a new region based segmentation method based on cloud model in order to take uncertainty into account in image segmentation. Firstly, cloud transform algorithm is given to determine the growing criteria, and then the region is transformed from quantitative pixel set to qualitative concept by backward cloud algorithm, finally cloud synthesis algorithm is realized to merge the two adjacent regions. Experiments show that the new method can extract target from background accurately, and more effectively than traditional image segmentation method.关键词：region growing;cloud model;uncertainty3776|285|0更新时间：2024-05-07
- 摘要：A novel shape representation and registration method based on Hough spectrum is developed in this paper. The weighted-average Hough spectrum(WAHS) is defined for the representation of arbitrary shapes, and the translation, rotation, scale and periodic properties of WAHS are summarized and proved. When registration, the parameters of rotation and scale can be estimated easily from the phase and amplitude of WAHS, and the parameter of translation can be estimated in the Hough density space. Experiments show that the method is effective to estimate the parameters of translation, rotation and scale, and is immune to noise and overlapping.关键词：shape representation;shape registration;weighted-average Hough spectrum(WAHS)3477|287|0更新时间：2024-05-07
- 摘要：PFMM(perspective fast marching method) is a successful approach to shape from shading (SFS) technique, but it is restricted by some conditions and sensitive to the precision of the initialization. In this paper, we have studied the characteristics of the coefficients in the Eikonal equation and proposed an improved perspective fast marching method based on adaptive Eikonal equation. This algorithm depends much less on the initialization which may have error from the real surface. Moreover we have proved that PFMM is a particular case of our algorithm. Experiments on synthetical pictures demonstrate that our algorithm can obtain higher accuracy than PFMM does and yield good performance for perspective SFS problem.关键词：shape from shading;Eikonal equation;fast marching method;adaptive Eikonal equation3063|245|0更新时间：2024-05-07
- 摘要：Level set method is an important numerical scheme to PDE image analysis, while the most serious problem is that level set is accompanied with high computation cost, slow speed, and especially frequent re-initialization. The paper carefully researches the disadvantages and presents a new initialization method based on mathematical morphology. The new method includes two schemes, i.e. smoothing scheme and reconstruction scheme, which perform two operations of smoothing inaccurate distance function and rebuilding narrow band separately using open, close and expansion operations. The proposed method is not only of high efficiency, but also can deal with the topology variations adaptively. This method can replace the conventional methods successfully and can also be applied in the real-time image processing.关键词：level set;initialization;narrow band;SDF;mathematical morphology3465|257|0更新时间：2024-05-07
- 摘要：The urban vegetation is a principal biological component of the urban landscape. Identifying and mapping the urban vegetation are important to urban management and planning. This paper presents a new object-based two-stage method to classify urban vegetation using airborne LiDAR data and high resolution aerial photographs through a case study of downtown Houston, USA. By exploiting the spectral information plus 2D geometric attributes from high resolution aerial photographs and 3D morphological information from airborne LiDAR data, a detailed and accurate classification of urban vegetation has been achieved. In the first stage, the aerial photographs are segmented into image objects. Based on the spectral and 2D geometric attributes, these objects are divided into six categories: non-shaded vegetation, shaded vegetation, water, building, open space, and shade. Vegetation objects, including non-shaded and shaded vegetation, are derived separately. In the second stage, the normalized Digital Surface Model derived from airborne LiDAR data is introduced to characterize the 3D geometric properties (height and roughness) of each vegetation object. Based on these properties, the vegetation objects are further classified into trees, shrubs/hedges, and grass-covered lawns. The overall classification accuracy of vegetation is analyzed and reported as high as 93.46%. The sources of errors are ascribed to the shade in aerial photo and the miscalculation of Digital Terrain Model from LiDAR data. This research suggests that the combination of morphological information of LiDAR and the spectral information from image data renders a powerful tool for a detailed investigation of urban vegetation.关键词：urban vegetation;object-based classification;two-stage classification;LiDAR;high resolution remote sensing image4271|297|0更新时间：2024-05-07
- 摘要：A study of internal waves occurring in the northeastern South China Sea with ENVISAT-ASAR data is presented. Using the remote sensing analyzing approach, a group of parameters of the internal waves is retrieved from synthesize aperture radar(SAR) image. The influence of the topographic variation on the propagation of internal waves is analyzed and the relation between the topographic variation and parameters of the internal waves is given. It is concluded that the direction of internal waves is incompletely consistent with the gradation of benthal topography and that the variation of topography on the shelf is one of the important factors of nonlinear effect on the propagation of internal waves. It is beneficial to research on internal waves’ theory and retrieval modeling for internal waves’ parameters using remote sensing data.关键词：synthesize aperture radar;internal waves;continental shelf slope;group velocity3238|259|0更新时间：2024-05-07
- 摘要：This paper introduces an adaptive watermarking algorithm for DEM. This proposed method can utilize human visual system(HVS), features of DEM data and discrete Fourier transform(DFT) to determine adaptively the location where the watermark can be hidden. And then, the watermark information is added to the lowness frequency of the texture region DFT. Experimental results show that the novel watermarking scheme for DEM has good imperceptibility, little effect on DEM accuracy and is robust to noise attack.关键词：digital elevation model;digital watermark;discrete Fourier transform;slope;accuracy;adaptive3362|277|0更新时间：2024-05-07
- 摘要：With the widespread use of map websites and on-line navigation systems, the need for multi-user concurrent queries for travel information is ever-increasing. In such a case, a bottleneck problem is how to improve the efficiencies of the multi-user concurrent path queries as much as possible, with only a controllable, as little as possible loss of the precisions of the query results. In this paper, an efficiency/accuracy trade-off control approach for the A* heuristic shortest path algorithm is presented, which fits a curve function of the heuristic factor, the efficiency and the accuracy with large samples, by the techniques of systematic sampling and intelligent symbolic regression. The efficiency and the accuracy of the A* algorithm are measured by the comparison with the Dijkstra exact algorithm. Through the use of the derived trade-off control model, the effective heuristic factor can be automatically determined with the input of the on-line user number and the required path accuracy, and as a result, the service response time for each user is much shortened.关键词：route planning;A* algorithm;trade-off control;intelligent symbolic regression3143|246|0更新时间：2024-05-07
- 摘要：The classic Chan-Vese model for two-phases segmentation of planar images is extended to image segmentation on implicit surfaces. The zero level set of a static level set function is used to express the surface on which images to be segmented are defined. Its intersection with another zero level set of a dynamic level set function is used to express spatial active contours for image segmentation. The novel energy functional includes three parts, the first one is the sum of square of the difference between pixel intensity and mean values in two regions on the surface. The second one is the length of spatial contour, and the third one is a penalty term to enforce the dynamic level set function to be a signed distance function. The evolution equation of the dynamic level set function is obtained using variation technique and is discretized with a simple explicit finite difference method. Experimental results validate the capacity of the proposed model in two phase image segmentation on implicit surfaces.关键词：implicit surface;image segmentation;Chan-Vese model;variational level set3386|216|0更新时间：2024-05-07
- 摘要：The SIFT algorithm is widely adopted by researchers in image and graphic study, with its many advantages such as invariance to scaling, rotation, noise and illumination changes. SIFT feature is based on local gradient, making it invulnerable to large scale of image extension, compression and rotation, and this meets the practical requirements of 3D object recognition. And the sensitivity to homographic transformation of the feature can be applied to partition the view space. Reasonably setting the threshold value, SIFT algorithm can handle the technical problems such as cutting the object from its background. After pre-processing, the high computation complexity can be reduced, making the system run in real time. Therefore, applying SIFT feature in view space partition, cutting the object from its background and pattern matching can effectively enhance the robustness of the system and improve its speed and efficiency.关键词：SIFT;3D object recognition;pattern match;view space partition4212|285|0更新时间：2024-05-07
- 摘要：Confusing panchromatic image and multispectral image can obtained clearer image the maltispectral image alone. A multiresolution image fusion algorithm based on watershed segmentation and wavelet transform is proposed. Firstly, we obtain the wavelet pyramid using the orthogonal wavelet transform. Then, watershed segmentation of the approximation image is computed, and the inverse wavelet transform is used to project this original segmentation up to the higher resolutions. After joint region analyzed, the joint region segmentation map is obtained, which is further used to guide the fusion of the wavelet coefficients. Finally, the inverse transform of the fused coefficients is implemented in order to obtain the final fusion image. The experimental results indicate that the algorithm is effective for the remote sensing image fusion, which can give consideration well to the spectral quality and spatial definition.关键词：image fusion;watershed segmentation;multi-solution;wavelet transform4289|305|0更新时间：2024-05-07
- 摘要：In the field of intelligence video surveillance, pedestrian detection is paid great attention to the security of daily life. In order to raise the detection rate, we combine partial features based on Adaboost with model matching. First, a new way of selecting proper partial feature is shown through analysis and comparison. Then, partial body is used in modeling which shows that model matching is combined in pedestrian detection. At last, experiments indicate that our method achieves a good result in pedestrian detection.关键词：pedestrian detection;partial feature;AdaBoost;model matching4164|277|0更新时间：2024-05-07
- 摘要：This paper presents a new approach to gait identification and authentication with simple representation and lower computational complexity, which can meet intelligent surveillance’s need in precision and response. It creates Gaussian Mixture Model for each scenario, and contour of gait is extracted from binary silhouette for Euclidean distance between the centroid and any pixel on it. Contour is unfolded clockwise by the distance from the uppermost pixel, and then 2D features are transformed into 1D and normalized according to a standard model of gait. Thresholds are determined by dynamic time warping (DTW) distance between training sequences and standard model. Finally, gait recognition is performed by comparing DTW distance of testing sequences with predetermined threshold. Compared with other methods, it balances both computational cost and recognition rate, and achieves performance of intelligent surveillance.关键词：gait recognition;feature extraction;dynamic time warping(DTW);intelligent surveillance4281|203|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