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
Automated detection of solar loops by the oriented connectivity method 用定向连接法自动检测太阳环
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1333766
Jong Kwan Lee, Timothy S Newman, G. A. Gary
{"title":"Automated detection of solar loops by the oriented connectivity method","authors":"Jong Kwan Lee, Timothy S Newman, G. A. Gary","doi":"10.1109/ICPR.2004.1333766","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1333766","url":null,"abstract":"An automated technique to segment solar coronal loops from intensity images of the sun's corona is introduced. It exploits physical characteristics of the solar magnetic field to enable robust extraction from noisy images. The technique is a constructive curve detection approach, constrained by collections of estimates of the magnetic field's orientation. Its effectiveness is evaluated through experiments on synthetic and real coronal images.","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":"124977108","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: 10
A parallel pipelined implementation of LOCO-I for JPEG-LS 用于JPEG-LS的LOCO-I的并行流水线实现
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1334311
M. Ferretti, M. Boffadossi
{"title":"A parallel pipelined implementation of LOCO-I for JPEG-LS","authors":"M. Ferretti, M. Boffadossi","doi":"10.1109/ICPR.2004.1334311","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334311","url":null,"abstract":"We describe N2C-EX/sup 1/, a parallel, pipelined version of a modified LOCO-I lossless compression algorithm used within the JPEG-LS coding scheme. This version takes into account the sequential nature of the original LOCO-I algorithm due to the use of context statistics in coding the residual errors of the predictive phase and uses three pipelines to carry out concurrently the encoding on independent pixels extracted from the serial stream of incoming data.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"69 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":"125079654","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
Shape retrieval using concavity trees 利用凹形树进行形状检索
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1334481
O. Badawy, M. Kamel
{"title":"Shape retrieval using concavity trees","authors":"O. Badawy, M. Kamel","doi":"10.1109/ICPR.2004.1334481","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334481","url":null,"abstract":"Concavity trees are well-known abstract structures. This paper proposes a new shape-based image retrieval method based on concavity trees. The proposed method has two main components. The first is an efficient (in terms of space and time) contour-based concavity tree extraction algorithm. The second component is a recursive concavity-tree matching algorithm that returns a distance between two trees. We demonstrate that concavity trees are able to boost the retrieval performance of two feature sets by at least 15% when tested on a database of 625 silhouette images.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"18 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":"125086788","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
A novel kernel prototype-based learning algorithm 一种新的基于核原型的学习算法
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1333849
A. K. Qin, P. N. Suganthan
{"title":"A novel kernel prototype-based learning algorithm","authors":"A. K. Qin, P. N. Suganthan","doi":"10.1109/ICPR.2004.1333849","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1333849","url":null,"abstract":"We propose a novel kernel prototype-based learning algorithm, called kernel generalized learning vector quantization (KGLYQ) algorithm, which can significantly improve the classification performance of the original generalized learning vector quantization algorithm in complex pattern classification tasks. In addition, the KGLVQ can also serve as a good general kernel learning framework for further investigation.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"40 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":"125125958","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: 58
An enhanced appearance model for ultrasound image segmentation 超声图像分割的增强外观模型
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.160
Yifeng Jiang, Zhijun Zhang, F. Cen, H. Tsui, Tze Kin Lau
{"title":"An enhanced appearance model for ultrasound image segmentation","authors":"Yifeng Jiang, Zhijun Zhang, F. Cen, H. Tsui, Tze Kin Lau","doi":"10.1109/ICPR.2004.160","DOIUrl":"https://doi.org/10.1109/ICPR.2004.160","url":null,"abstract":"Active appearance model (AAM) had been popular on object segmentation for medical images. However, its performance is not good on ultrasound (US) images. In this paper, we propose an enhanced appearance model which represents the texture by edge structure and reduces the view-dependent feature of US images by a novel data normalization process. In our experiments on general US data, the proposed model shows considerable improvements compared to the original one.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"91 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":"126068029","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
Integration of range images in a multi-view stereo system 多视点立体系统中距离图像的集成
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1333758
X. Ju, T. Boyling, J. Siebert, N. McFarlane, Jiahua Wu, R. Tillett
{"title":"Integration of range images in a multi-view stereo system","authors":"X. Ju, T. Boyling, J. Siebert, N. McFarlane, Jiahua Wu, R. Tillett","doi":"10.1109/ICPR.2004.1333758","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1333758","url":null,"abstract":"A novel method for integrating multiple range images in a multi-view stereo imaging system is presented here. Due to self-occlusion an individual range image provides only a partial model of an object surface. Therefore multiple range images from differing viewpoints must be captured and merged to extend the surface area that can be captured. In our approach range images are decomposed into subset patches and then evaluated in a \"confidence competition\". Redundant patches are removed whilst winning patches are merged to complete a single plausible mesh that represents the acquired object surface.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"32 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":"123197997","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: 10
A fast discriminant approach to active object recognition and pose estimation 一种快速判别的主动目标识别与姿态估计方法
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1334476
C. Laporte, Rupert Brooks, T. Arbel
{"title":"A fast discriminant approach to active object recognition and pose estimation","authors":"C. Laporte, Rupert Brooks, T. Arbel","doi":"10.1109/ICPR.2004.1334476","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334476","url":null,"abstract":"This paper presents a new criterion for viewpoint selection in the context of active Bayesian object recognition and pose estimation. Recognition is performed by probabilistically fusing successive observations with the current belief state of the system. Based on the current belief state, the next viewpoint is chosen to maximize the expected discriminability of the current competing hypotheses. Experiments on a difficult database of aircraft models show that this approach achieves comparable recognition performance to the widely used information theoretic approaches at a much lower computational cost.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"81 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":"123427088","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
Image disocclusion using a probabilistic gradient orientation 使用概率梯度方向的图像去闭塞
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1334034
Emmanuel Villéger, G. Aubert, L. Blanc-Féraud
{"title":"Image disocclusion using a probabilistic gradient orientation","authors":"Emmanuel Villéger, G. Aubert, L. Blanc-Féraud","doi":"10.1109/ICPR.2004.1334034","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334034","url":null,"abstract":"We devise a new method to remove occlusions in an image by using its level-lines. We take into account the error in the computation of their orientation by introducing a field of probabilities for the level-lines orientations. We use second order partial differential equations for this field and the image to interpolate in the occluded part.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"44 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":"125270887","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
Multi-resolution template kernels 多分辨率模板内核
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1334138
C. Needham, R. Boyle
{"title":"Multi-resolution template kernels","authors":"C. Needham, R. Boyle","doi":"10.1109/ICPR.2004.1334138","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334138","url":null,"abstract":"Domains in which shapes of objects change rapidly and significantly are a challenge for existing representation techniques: sport is a good example of this. We present a texture-based approach that copes with these problems in addition to resolution variation. A set of exemplar poses are learned from subsampled example images of the target object, creating a set of multi-resolution template kernels which when convolved with the image respond suitably. This technique may then be used in established tracking algorithms (e.g. CONDENSATION [Isard, M et al., 1996]). We demonstrate the technique in two domains, and suggest a Markov approach using it to model behaviour.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"32 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":"125483215","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
Face pose estimation and its application in video shot selection 人脸姿态估计及其在视频镜头选择中的应用
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. Pub Date : 2004-08-23 DOI: 10.1109/ICPR.2004.1334117
Zhiguang Yang, H. Ai, Bo Wu, S. Lao, Lianhong Cai
{"title":"Face pose estimation and its application in video shot selection","authors":"Zhiguang Yang, H. Ai, Bo Wu, S. Lao, Lianhong Cai","doi":"10.1109/ICPR.2004.1334117","DOIUrl":"https://doi.org/10.1109/ICPR.2004.1334117","url":null,"abstract":"In this paper, a face pose estimation method and its application in video shot selection for face image preprocessing is introduced. The pose estimator is learned by a boosting regression algorithm called SquareLev.R that learns poses from simple Haar-type features. It consists of two tree structured subsystems for the left-right angle and up-down angle respectively. As a specific application in video based face recognition, the best shot selection problem is discussed, which results in a real-time system that can automatically select the most frontal face from a video sequence.","PeriodicalId":335842,"journal":{"name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","volume":"29 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":"125493700","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: 34
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