Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237)最新文献

Real time video distribution using publication through a database 通过数据库使用出版物进行实时视频分发

Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237) Pub Date : 1998-01-20 DOI: 10.1109/SIBGRA.1998.722752

I. Diamantis, A. Ntalakas, M. Strintzis

引用次数: 1

Pipeline stereo matching in binary images 二值图像中的管道立体匹配

Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237) Pub Date : 1998-01-20 DOI: 10.1109/SIBGRA.1998.722782

L. Gonçalves, A.A.F. De Oliveira

引用次数: 5

Visual processing throughout the visual field 整个视野的视觉处理

Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237) Pub Date : 1998-01-20 DOI: 10.1109/SIBGRA.1998.722725

J. Faubert

引用次数: 7

A unified geometric model for 3D confocal image analysis in cytology 细胞学中三维共聚焦图像分析的统一几何模型

Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237) Pub Date : 1998-01-20 DOI: 10.1109/SIBGRA.1998.722735

Alessandro Sarti, C. Ortíz, S. Lockett, R. Malladi

引用次数: 19

Two frontiers in morphological image analysis: differential evolution models and hybrid morphological/linear neural networks 形态学图像分析的两个前沿:差分进化模型和混合形态学/线性神经网络

Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237) Pub Date : 1998-01-20 DOI: 10.1109/SIBGRA.1998.722726

P. Maragos, M. A. Butt, Lúcio F. C. Pessoa

{"title":"Two frontiers in morphological image analysis: differential evolution models and hybrid morphological/linear neural networks","authors":"P. Maragos, M. A. Butt, Lúcio F. C. Pessoa","doi":"10.1109/SIBGRA.1998.722726","DOIUrl":"https://doi.org/10.1109/SIBGRA.1998.722726","url":null,"abstract":"We briefly describe advancements in two broad areas of morphological image analysis. Part I deals with differential morphology and curve evolution. The partial differential equations (PDEs) that model basic morphological operations are first presented. The resulting dilation PDE, numerically implemented by curve evolution algorithms, improves the accuracy of morphological multiscale analysis by Euclidean disks and (its anisotropic/heterogeneous version) is the basic ingredient of PDE models that solve image analysis problems such as gridless halftoning and watershed segmentation based on the eikonal PDE. Part II deals with morphology-related systems for pattern recognition. It presents a general class of multilayer feedforward neural networks where the combination of inputs in every node is formed by hybrid linear and nonlinear (of the morphological/rank type) operations. For its design a methodology is formulated using ideas from the backpropagation algorithm and robust techniques are developed to circumvent the non-differentiability of rank functions. Experimental results in handwritten character recognition are described and illustrate some of the properties of this new type of neural nets.","PeriodicalId":282177,"journal":{"name":"Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133718376","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

Levelings and morphological segmentation 调平和形态分割

Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237) Pub Date : 1998-01-20 DOI: 10.1109/SIBGRA.1998.722729

F. Meyer

引用次数: 16

Interface: a real time facial animation system 界面:一个实时面部动画系统

Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237) Pub Date : 1998-01-20 DOI: 10.1109/SIBGRA.1998.722751

José Daniel Ramos Wey, J. A. Zuffo, LSI-Laboratório de Sistemas Integráveis

引用次数: 6

Towards optimal ranking metrics 走向最优排名指标

Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237) Pub Date : 1998-01-20 DOI: 10.1109/SIBGRA.1998.722776

N. Sebe, M. Lew, D. P. Huijsmans

引用次数: 2

Biased clustering methods for image classification 图像分类的有偏聚类方法

Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237) Pub Date : 1998-01-20 DOI: 10.1109/SIBGRA.1998.722761

R. Santos, T. Ohashi, T. Yoshida, T. Ejima

{"title":"Biased clustering methods for image classification","authors":"R. Santos, T. Ohashi, T. Yoshida, T. Ejima","doi":"10.1109/SIBGRA.1998.722761","DOIUrl":"https://doi.org/10.1109/SIBGRA.1998.722761","url":null,"abstract":"Classification of image data can be done using supervised or unsupervised methods. Each approach has advantages and disadvantages: supervised methods require labeled samples in order to create signatures or discriminating functions to classify unknown data, which at the end of the process will have class labels attached to it. Unsupervised methods, usually based on clustering, do not require samples for the classes, but their result will be unlabeled, requiring additional processing steps to attach labels to pixels on images. In this paper a new method for classification is presented, called biased clustering, which will use imprecise information about classes to create expectancies for assignment of a pixel to a class. These expectancies will be validated or corrected by a clustering method. The advantage over supervised methods is that the samples for the classes does not need to be precisely labeled, and can be derived with simple image processing methods. The advantage over basic clustering methods is that the pixels will be labeled at the end of the classification. An application of the method will be presented, and results will be discussed.","PeriodicalId":282177,"journal":{"name":"Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124784008","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: 1

Reconstructing a 3D model from range images using radial flow model 利用径向流模型从距离图像重建三维模型

Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237) Pub Date : 1998-01-20 DOI: 10.1109/SIBGRA.1998.722733

R. Marques da Silva, Wu Shin-Ting

引用次数: 3