发布求助
文献互助 智能选刊 最新文献

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.最新文献

筛选
英文 中文
Gaussian noise elimination in colour images by vector-connected filters 矢量连接滤波器在彩色图像中的高斯噪声消除
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.409
F. Ortiz, Fernando Torres Medina, P. Gil
{"title":"Gaussian noise elimination in colour images by vector-connected filters","authors":"F. Ortiz, Fernando Torres Medina, P. Gil","doi":"10.1109/ICPR.2004.409","DOIUrl":"https://doi.org/10.1109/ICPR.2004.409","url":null,"abstract":"This paper deals with the use of vector-connected filters for eliminating Gaussian noise in colour images. This class of morphological filters suppresses noise but preserves the contours of the objects. We impose a total order between pixels for morphological processing. Once the HSI space has been adapted, we employ it in the lexicographical order. As such, all of the morphological operations are vectorial. After having defined the vectorial geodesic operators, they are then employed to eliminate Gaussian noise.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130130821","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
Active mass estimation with haptic vision 基于触觉视觉的主动质量估计
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1334516
Shiro Tanaka, T. Tanigawa, Yoshinobu Abe, Masatsugu Uejo, Hiromi T. Tanaka
{"title":"Active mass estimation with haptic vision","authors":"Shiro Tanaka, T. Tanigawa, Yoshinobu Abe, Masatsugu Uejo, Hiromi T. Tanaka","doi":"10.1109/ICPR.2004.1334516","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334516","url":null,"abstract":"Real-world objects exhibit rich physical interaction behaviors on contact. Such behaviors depend on how heavy and hard it is when hold, how its surface feels when touched, how it deforms on contact, etc. Recently, there are growing needs for haptic exploration to estimate and extract such physical object properties as mass, friction, elasticity, etc. In this paper, we propose an active mass estimation method based on haptic vision. We first observe an object with active vision to extract its 3D shape and posture. Next, we estimate a contact point and contact force and apply it to cause the object to move without rotation by a robot hand. We observe changes in the contact force using a force feedback sensor, and also observe its straight movement using a CCD camera. Then, we estimate the mass of the object using known static and dynamic friction coefficients. Experimental results show that the mass of solids such as wood, iron, and ceramic objects were estimated efficiently within 10% error bound.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130258949","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
Linear and non-linear geometric object matching with implicit representation 线性和非线性几何对象匹配与隐式表示
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1334627
A. Leow, M. Chiang, H. Protas, P. Thompson, L. Vese, Henry S. C. Huang
{"title":"Linear and non-linear geometric object matching with implicit representation","authors":"A. Leow, M. Chiang, H. Protas, P. Thompson, L. Vese, Henry S. C. Huang","doi":"10.1109/ICPR.2004.1334627","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334627","url":null,"abstract":"This paper deals with the matching of geometric objects including points, curves, surfaces, and subvolumes using implicit object representations in both linear and non-linear settings. This framework can be applied to feature-based non-linear image warping in biomedical imaging with the deformation constrained to be one-to-one, onto, and diffeomorphic. Moreover, a theoretical connection is established between the well known Hausdorff metric and the framework proposed in this paper. A general strategy for matching geometric objects in both 2D and 3D is discussed. The corresponding Euler-Lagrange equations are presented and gradient descent method is employed to solve the time dependent partial differential equations.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130282422","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
Optimally regularised kernel Fisher discriminant analysis 最优正则化核Fisher判别分析
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1334245
Kamel Saadi, N. L. C. Talbot, G. Cawley
{"title":"Optimally regularised kernel Fisher discriminant analysis","authors":"Kamel Saadi, N. L. C. Talbot, G. Cawley","doi":"10.1109/ICPR.2004.1334245","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334245","url":null,"abstract":"Mika et al. (1999) introduce a non-linear formulation of Fisher's linear discriminant, based the now familiar \"kernel trick\", demonstrating state-of-the-art performance on a wide range of real-world benchmark datasets. In this paper, we show that the usual regularisation parameter can be adjusted so as to minimise the leave-one-out cross-validation error with a computational complexity of only O(/spl lscr//sup 2/) operations, where /spl lscr/ is the number of training patterns, rather than the O(/spl lscr//sup 4/) operations required for a naive implementation of the leave-one-out procedure. This procedure is then used to form a component of an efficient hierarchical model selection strategy where the regularisation parameter is optimised within the inner loop while the kernel parameters are optimised in the outer loop.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134019355","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: 6
Retrieval of on-line hand-drawn sketches 检索在线手绘草图
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1334330
A. Namboodiri, Anil K. Jain
{"title":"Retrieval of on-line hand-drawn sketches","authors":"A. Namboodiri, Anil K. Jain","doi":"10.1109/ICPR.2004.1334330","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334330","url":null,"abstract":"Sketch matching algorithms are commonly used for indexing and retrieval of documents based on printed or hand-drawn sketches. One could use a hand-held computer to do sketch-based queries to a database containing hand-drawn and printed sketches. We present an on-line hand-drawn sketch matching algorithm based on a line-based representation of sketches. A distance measure is defined for comparing two sketches based on this representation. The algorithm is computationally efficient and achieves a recall rate of 88.44% at the same precision, when tested on a database of 150 sketches collected from 5 users.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131486317","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: 13
Velocity adaptation of space-time interest points 时空兴趣点的速度自适应
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1334003
I. Laptev, T. Lindeberg
{"title":"Velocity adaptation of space-time interest points","authors":"I. Laptev, T. Lindeberg","doi":"10.1109/ICPR.2004.1334003","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334003","url":null,"abstract":"The notion of local features in space-time has recently been proposed to capture and describe local events in video. When computing space-time descriptors, however, the result may strongly depend on the relative motion between the object and the camera. To compensate for this variation, we present a method that automatically adapts the features to the local velocity of the image pattern and, hence, results in a video representation that is stable with respect to different amounts of camera motion. Experimentally we show that the use of velocity adaptation substantially increases the repeatability of interest points as well as the stability of their associated descriptors. Moreover, for an application to human action recognition we demonstrate how velocity-adapted features enable recognition of human actions in situations with unknown camera motion and complex, non-stationary backgrounds.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131499740","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: 84
Method for early diagnostics of lymphatic system tumors on the basis of the analysis of chromatin constitution in cell nucleus images 基于细胞核图像染色质构成分析的淋巴系统肿瘤早期诊断方法
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1334651
I. Gurevich, D. Murashov
{"title":"Method for early diagnostics of lymphatic system tumors on the basis of the analysis of chromatin constitution in cell nucleus images","authors":"I. Gurevich, D. Murashov","doi":"10.1109/ICPR.2004.1334651","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334651","url":null,"abstract":"In this paper, a new criterion for early diagnostics of lymphatic system tumor from images of cell nuclei of lymphatic nodes is considered. A method for image analysis of chromatin structure is developed on the basis of the scale-space approach. A diagnostically important criterion is defined as a total amount of points of spatial intensity extrema in the families of blurred images generated by the given image of a cell nucleus. The procedure for calculating criterion values is presented. Testing of the obtained criterion is carried out.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131711793","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
Robust facet model for application to speckle noise removal 鲁棒面模型在散斑噪声去除中的应用
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1334354
K. Eom
{"title":"Robust facet model for application to speckle noise removal","authors":"K. Eom","doi":"10.1109/ICPR.2004.1334354","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334354","url":null,"abstract":"A robust facet model is developed, and applied to speckle noise removal in synthetic aperture radar (SAR) images. The parameters of a facet model are usually estimated by a least-squares (LS) method under the Gaussian assumption. In many applications, such as speckle removal in SAR images, the noise process is not Gaussian, and conventional estimators do not work. A robust estimation algorithm is developed, and applied to remove speckle noise in synthetic aperture images. Conventional adaptive filtering approaches in speckle filtering smoothes the image selectively depending on the details of underlying textures, and tend to blur details after speckle removal. In the proposed approach, the image is assumed to be composed of structural and stochastic components, and the stochastic component is modeled by a robust facet model. The proposed method is applied to real synthetic aperture images to demonstrate the validity and effectiveness of the algorithm.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131765207","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: 4
Historical document image enhancement using background light intensity normalization 历史文献图像增强使用背景光强度归一化
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1334167
Zhixin Shi, V. Govindaraju
{"title":"Historical document image enhancement using background light intensity normalization","authors":"Zhixin Shi, V. Govindaraju","doi":"10.1109/ICPR.2004.1334167","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334167","url":null,"abstract":"This work presents a background light intensity normalization algorithm suitable for historical document images. The algorithm uses an adaptive linear function to approximate the uneven background due to the uneven surface of the document paper, aged color and light source of the cameras for image lifting. Our algorithm adaptively captures the background with a \"best fit\" linear function and normalized with respect to the approximation. The technique works for both gray scale and color images with significant improvement in readability.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131765453","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: 90
Evaluation of fingerprint orientation field registration algorithms 指纹方向场配准算法的评价
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1333854
Neil Yager, A. Amin
{"title":"Evaluation of fingerprint orientation field registration algorithms","authors":"Neil Yager, A. Amin","doi":"10.1109/ICPR.2004.1333854","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1333854","url":null,"abstract":"The majority of modern, fingerprint registration algorithms are based on the alignment of minutiae features. However, shortcomings of this approach are becoming apparent due to the difficulty of extracting minutiae from noisy or low quality images. This papers explores a novel approach to fingerprint registration based on orientation field alignment. One main advantage of this method is that orientation fields can be computed reliably for poor quality images, providing a robust feature for registration. Three orientation field alignment algorithms are presented, and their performance is evaluated using an FVC2002 dataset.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131837151","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: 14
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：481959085
Book学术官方微信