发布求助
文献互助 智能选刊 最新文献

Fourth International Conference on Image and Graphics (ICIG 2007)最新文献

筛选
英文 中文
Modified Luminance Based Adaptive MSR 基于改进亮度的自适应MSR
Fourth International Conference on Image and Graphics (ICIG 2007) Pub Date : 2007-08-22 DOI: 10.1109/ICIG.2007.137
Bo Sun, Weifang Chen, Hongyu Li, W. Tao, Jiang Li
{"title":"Modified Luminance Based Adaptive MSR","authors":"Bo Sun, Weifang Chen, Hongyu Li, W. Tao, Jiang Li","doi":"10.1109/ICIG.2007.137","DOIUrl":"https://doi.org/10.1109/ICIG.2007.137","url":null,"abstract":"A modified luminance based adaptive MSR is proposed in this paper. This new method addresses the problems existing in standard Retinex algorithms, such as halo artifacts and incorrect colors. The paper chooses an adaptive Gaussian function whose shape follows edges of image, thus reducing the artifacts along high contrast edges. In addition, only the luminance channel instead of all color bands is processed, which can produce a more consistent and reliable color rendition.","PeriodicalId":367106,"journal":{"name":"Fourth International Conference on Image and Graphics (ICIG 2007)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124928522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 18
The Procedure Geometry Detail Enhancement Algorithm of Chunklod 块体的过程几何细节增强算法
Fourth International Conference on Image and Graphics (ICIG 2007) Pub Date : 2007-08-22 DOI: 10.1109/ICIG.2007.178
Yanchun Shen, You-hong Zhu, Zhuan-ping Wen, Li Cao
{"title":"The Procedure Geometry Detail Enhancement Algorithm of Chunklod","authors":"Yanchun Shen, You-hong Zhu, Zhuan-ping Wen, Li Cao","doi":"10.1109/ICIG.2007.178","DOIUrl":"https://doi.org/10.1109/ICIG.2007.178","url":null,"abstract":"This paper represents the Procedure geometry detail enhancement algorithm of Chunklod. The enhancement algorithm adopts massive model as processing unit. Because the Chunklod algorithm lacks process that viewpoint is near to the ground. The enhancement algorithm improves the efficiency of rendering by combining the local triangle surface simplified algorithm and the error evaluation & control algorithm, it avoids large-scale computing caused by over-LOD. Finally ,the paper shows that the visual effect of terrain information is expressed well when the algorithm is working virtually-taking the geographical information system for example .The results indicates that the improved level of detail enhancement of ChunkLod is a practical terrain algorithm with total levels of detail technology.","PeriodicalId":367106,"journal":{"name":"Fourth International Conference on Image and Graphics (ICIG 2007)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130323234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
A Practical Calibration Method for Multiple Cameras 一种实用的多相机标定方法
Fourth International Conference on Image and Graphics (ICIG 2007) Pub Date : 2007-08-22 DOI: 10.1109/ICIG.2007.29
Liuxin Zhang, Bin Li, Yunde Jia
{"title":"A Practical Calibration Method for Multiple Cameras","authors":"Liuxin Zhang, Bin Li, Yunde Jia","doi":"10.1109/ICIG.2007.29","DOIUrl":"https://doi.org/10.1109/ICIG.2007.29","url":null,"abstract":"In this paper, we propose a practical factorization- and-position based method for multiple cameras calibration. The method yields a simple calibration means for an arbitrary number of linear projective cameras while maintaining the handiness and flexibility of the original method. A freely moving planar pattern as a calibration object at a few different orientations is only required. All the cameras do not have to see this pattern at all orientations, and only reasonable overlap between camera subgroups is necessary. We divide these cameras into groups according to their positions and orientations first, and then calibrate each camera in the world coordinate system of its own group via a factorization-based method. Common view fields of planar pattern are used to estimate the Euclidean transformation between these world coordinate systems and represent all cameras in a same world coordinate system. Both the intrinsic and extrinsic parameters of cameras can be obtained in a uniform world coordinate system of accuracy to within a pixel.","PeriodicalId":367106,"journal":{"name":"Fourth International Conference on Image and Graphics (ICIG 2007)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128139957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 29
Magnifying Binary Image based on Morphology 基于形态学的二值图像放大
Fourth International Conference on Image and Graphics (ICIG 2007) Pub Date : 2007-08-22 DOI: 10.1109/ICIG.2007.129
Yajuan Wu, Minghui Wang, Xiaofeng Liu
{"title":"Magnifying Binary Image based on Morphology","authors":"Yajuan Wu, Minghui Wang, Xiaofeng Liu","doi":"10.1109/ICIG.2007.129","DOIUrl":"https://doi.org/10.1109/ICIG.2007.129","url":null,"abstract":"When a binary image is magnified, many jaggy corners are generated from traditional interpolated methods. In this paper, an interpolated method using mathematical morphology is presented. After magnifying the original image using nearest neighbor interpolation, jaggy corners that have different shapes are mined and stored in a matrix named Corners. Then colors of pixels listed in Corners and their neighboring pixels are changed. Thus, jaggy corners in the image are eliminated and the visual quality of the image is improved sufficiently.","PeriodicalId":367106,"journal":{"name":"Fourth International Conference on Image and Graphics (ICIG 2007)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114450151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 8
MODIS Image Compression with Optimal Inter-band Prediction and Integer Wavelet Transform 基于最优带间预测和整数小波变换的MODIS图像压缩
Fourth International Conference on Image and Graphics (ICIG 2007) Pub Date : 2007-08-22 DOI: 10.1109/ICIG.2007.138
Yuan-xiang Li, Li Deng, Zhongliang Jing
{"title":"MODIS Image Compression with Optimal Inter-band Prediction and Integer Wavelet Transform","authors":"Yuan-xiang Li, Li Deng, Zhongliang Jing","doi":"10.1109/ICIG.2007.138","DOIUrl":"https://doi.org/10.1109/ICIG.2007.138","url":null,"abstract":"In order to store and transmit MODIS (moderate resolution imaging spectro-radiometer) multispectral images effectively, a practical compression method using optimal inter-band prediction and integer wavelet transform (IWT) is proposed. First, MODIS intrinsic noises are removed. Then, an optimal inter-band predictor is designed for de-correlating the spectral redundancy, and an error image is produced. Next, spatial redundancy in the error image is removed by using IWT and SPIHT (set partitioning in hierarchical trees) algorithm. This method can implement lossless compression, quasi-lossless compression and lossy compression with high compression ratio. We demonstrate the compression performance with different compression schemes in details. The experimental results have shown that our proposed method is efficient and practical for MODIS images.","PeriodicalId":367106,"journal":{"name":"Fourth International Conference on Image and Graphics (ICIG 2007)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124398285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 11
Rendering of Translucent Objects Based upon PRT 基于PRT的半透明物体渲染
Fourth International Conference on Image and Graphics (ICIG 2007) Pub Date : 2007-08-22 DOI: 10.1109/ICIG.2007.158
Jin Zhou, Zhang Jiawan, Sun Jizhou
{"title":"Rendering of Translucent Objects Based upon PRT","authors":"Jin Zhou, Zhang Jiawan, Sun Jizhou","doi":"10.1109/ICIG.2007.158","DOIUrl":"https://doi.org/10.1109/ICIG.2007.158","url":null,"abstract":"A framework to incorporate subsurface scattering effects is proposed in this paper based on precomputed light transport technology, which can interactively rerender translucent objects. First, the complete BSSRDF model is considered and the two-pass hierarchical technique by [5] in the space of non-linearly approximated transport vectors is applied, which efficiently evaluate transport vectors due to diffuse multiple scattering. Single scattering is also incorporated by considering [16] 's approximation. For a general phase function, a technique from BRDF rendering is extended which using a separable decomposition to allow decoupled precomputation and rendering [8]. Using this approach, interactive frame rates with comparable speed to the state-of-the-art systems is achieved.","PeriodicalId":367106,"journal":{"name":"Fourth International Conference on Image and Graphics (ICIG 2007)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116895342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Constructing Support Vector Machine Kernels from Orthogonal Polynomials for Face and Speaker Verification 基于正交多项式构造支持向量机核用于人脸和说话人验证
Fourth International Conference on Image and Graphics (ICIG 2007) Pub Date : 2007-08-22 DOI: 10.1109/ICIG.2007.77
Feng Zhou, Zhigang Fang, Jie Xu
{"title":"Constructing Support Vector Machine Kernels from Orthogonal Polynomials for Face and Speaker Verification","authors":"Feng Zhou, Zhigang Fang, Jie Xu","doi":"10.1109/ICIG.2007.77","DOIUrl":"https://doi.org/10.1109/ICIG.2007.77","url":null,"abstract":"This paper presents an alternative to construct support vector machine (SVM) kernels from orthogonal polynomials. After describing some knowledge about orthogonal polynomials, we construct kernels from orthogonal polynomials according to Mercer's condition. The elegant and fascinating characteristics of the orthogonal polynomials promise the minimum data redundancy in feature space and make it possible to represent the data with less support vectors. Experimental results show that the SVMs with orthogonal polynomial kernels outperform that with traditional kernels in terms of generalization power and less support vectors.","PeriodicalId":367106,"journal":{"name":"Fourth International Conference on Image and Graphics (ICIG 2007)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117184279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
Blind Image Restoration Using Improved APEX Method with Pre-denoising 基于预去噪的改进APEX盲图像复原方法
Fourth International Conference on Image and Graphics (ICIG 2007) Pub Date : 2007-08-22 DOI: 10.1109/ICIG.2007.65
Jianlin Zhang, Qiheng Zhang
{"title":"Blind Image Restoration Using Improved APEX Method with Pre-denoising","authors":"Jianlin Zhang, Qiheng Zhang","doi":"10.1109/ICIG.2007.65","DOIUrl":"https://doi.org/10.1109/ICIG.2007.65","url":null,"abstract":"Loss of image quality due to degradation has seriously bad effect on the post-analyzing and postprocessing of image. Blind restoration of degraded image is usually required to improve the image quality, for the reason that the degradation is partially or completely unknown in many practical situations. Commonly, using the APEX method can effectively accomplish the blind restoration when a significant class of degradation (Levy stable processes) is considered, but noise is unexpectedly amplified in the process. In this paper, a novel method is proposed to both suppress the noise effect and improve the image quality. The performance of the method is investigated with experiments on real degraded images. The noniterative property of this method makes its application and implementation in real-time image processing systems be easy.","PeriodicalId":367106,"journal":{"name":"Fourth International Conference on Image and Graphics (ICIG 2007)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115585362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 9
Modeling Expressive Wrinkles of Face For Animation 建模表情皱纹的脸的动画
Fourth International Conference on Image and Graphics (ICIG 2007) Pub Date : 2007-08-22 DOI: 10.1109/ICIG.2007.136
Ming Li, Baocai Yin, Dehui Kong, Xiaonan Luo
{"title":"Modeling Expressive Wrinkles of Face For Animation","authors":"Ming Li, Baocai Yin, Dehui Kong, Xiaonan Luo","doi":"10.1109/ICIG.2007.136","DOIUrl":"https://doi.org/10.1109/ICIG.2007.136","url":null,"abstract":"Vivid facial expressions contribute greatly to the visual realism of 3D face models. However, it is often tedious and expensive to model facial details which are authentic and real-time. In this paper, a simple and functional approach for modeling dynamic wrinkles of face is introduced. Started with structured facial mesh, we divide face region into some wrinkle subregions, and create some wrinkle lines with our algorithm in these subregions. Then, some key nodes are labeled on the facial mesh, these key nodes affect wrinkle lines if wrinkle lines locate the subregions that abut on the key nodes. With our algorithm, motion of wrinkle lines is produced by movement of key nodes. Consequently, wrinkle lines drive facial mesh to model expressive wrinkles. In this way, we create dynamic and functional expressive wrinkles of individuals available to date and demonstrate their use in facial animation.","PeriodicalId":367106,"journal":{"name":"Fourth International Conference on Image and Graphics (ICIG 2007)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123090969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 20
Content-based Table Tennis Games Highlight Detection Utilizing Audiovisual Clues 基于内容的乒乓球游戏利用视听线索突出检测
Fourth International Conference on Image and Graphics (ICIG 2007) Pub Date : 2007-08-22 DOI: 10.1109/ICIG.2007.78
Bin Zhang, Wei Chen, W. Dou, Yujin Zhang, Liming Chen
{"title":"Content-based Table Tennis Games Highlight Detection Utilizing Audiovisual Clues","authors":"Bin Zhang, Wei Chen, W. Dou, Yujin Zhang, Liming Chen","doi":"10.1109/ICIG.2007.78","DOIUrl":"https://doi.org/10.1109/ICIG.2007.78","url":null,"abstract":"Both audio and video are considered as important information carriers of multimedia content. In this paper, we propose an algorithm utilizing audiovisual clues for a scenario of sports game highlight detection, where the highlight detection for table tennis games are studied. Since audio and video contain different aspects of information that is helpful to locate highlights, we build two algorithms detecting highlight candidates based on audio and video, respectively, where hidden Markov model (HMM) audio keyword modeling and unsupervised shot clustering are applied. Decision fusion is invoked to combine audio and video highlight candidates and generate final highlights. Promising experimental results up to 90 % average precision are achieved.","PeriodicalId":367106,"journal":{"name":"Fourth International Conference on Image and Graphics (ICIG 2007)","volume":"161 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115691649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 9
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信