显著性轮廓提取、轮廓编组综述要看的内容(二)Stochastic Completion Fields学派

news/2024/7/8 15:35:11 标签: shapes, properties, parallel, distance, structure, image

Stochastic Completion Fields学派

97年提出来后来好像没啥发展了。。。

David W. Jacobs

92 年从MIT博士毕业,师从Eric Grimson。现在是Maryland大学的A.P.。关注的问题是图像中目标的识别,知觉组织方面研究的大牛,做了很多知觉组织方面计算的和心理学方 面的研究。知觉组织干的事情是,如何在识别目标前就将目标标记出来。Jacobs认为,知觉组织是识别所必须的过程,他做了研究展示二者的结合。

Perceptual Organization

· D. Jacobs, ``What Makes Viewpoint Invariant Properties Perceptually Salient?'' , JOSA (A), 2003.

· Z. Liu, D. Jacobs, R. Basri ``The role of convexity in perceptual completion -- beyond good continuation'' . Vision Research 39: 4244-4257, 1999. 

· D. Jacobs, ``Robust and Efficient Detection of Convex Groups'' , IEEE Trans. PAMI, 18 (1):23-37, 1996. Copyright (c) 1996 by IEEE.

· L. Williams, and D. Jacobs ``Local Parallel Computation of Stochastic Completion Fields'' ,  Neural Computation , 9 (4):859-881, 1997.  

· L. Williams and D. Jacobs ``Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience'' , Neural Computation , 9 (4):837-858, 1997. 

Lance R. Williams

94年,马萨诸塞州大学博士毕业,题目是:Perceptual Completion of Occluded Surfaces 。在NEC研究中心做过博士后,现在是新墨西哥大学的A.P.。跟Jacobs应该是在NEC的时候是好哥们儿,随机完全场的理论也是他们那个期间提出来的。现在在学术领域已经不活跃了。

Zweck, J.W. and L.R. Williams, Euclidean Group Invariant Computation of Stochastic Completion Fields Using Shiftable-Twistable Functions , Journal of Mathematical Imaging and Vision 21(2), pp. 135-154, 2004.

Mahamud, S., Williams, L.R., Thornber, K.K. and K. Xu, Segmentation of Multiple Salient Closed Contours from Real Images , IEEE Trans. on Pattern Analysis and Machine Intelligence 25(4), pp. 433-444, 2003.

Williams, L.R. and K.K. Thornber, Orientation, Scale, and Discontinuity as Emergent Properties of Illusory Contour Shape , Neural Computation 13(8), pp. 1683-1711, 2001.

Thornber, K.K. and L.R. Williams, Characterizing the Distribution of Completion Shapes with Corners Using a Mixture of Random Processes , Pattern Recognition 33, pp. 543-553, 2000.

Williams, L.R., Zweck, J.W., Wang, T. and K.K. Thornber, Computing Stochastic Completion Fields in Linear-Time Using a Resolution Pyramid , Computer Vision and Image Understanding 76(3), pp. 289-297, 1999.

Williams, L.R. and K.K. Thornber, A Comparison of Measures for Detecting Natural Shapes in Cluttered Backgrounds , Intl. Journal of Computer Vision 34 (2/3), pp. 81-96, 1999.

Williams, L.R. and D.W. Jacobs, Local Parallel Computation of Stochastic Completion Fields , Neural Computation 9(4), pp. 859-881, 1997.

Williams, L.R. and D.W. Jacobs, Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience , Neural Computation 9(4), pp. 837-858, 1997.

Thornber, K.K. and L.R. Williams, Analytic Solution of Stochastic Completion Fields , Biological Cybernetics 75, pp. 141-151, 1996.

Williams, L.R. and A.R. Hanson, Perceptual Completion of Occluded Surfaces , Computer Vision and Image Understanding 64(1), pp. 1-20, 1996.

他还有一个硕士学生,也做显著性闭合轮廓,硕士论文题目是:Improved Segmentation of Salient Closed Contours

Shyjan Mahamud

02年从CMU博士毕业,题目是Discriminative Distance Measures for Object Detection 。研究兴趣是目标识别,知觉组织,机器学习,Structure from Motion。貌似现在已近不在学术界了。

在我所关注的contour grouping方面的研究,还是基于Jacobs和Williams在97年提出的Stochastic Completion Fields。

Segmentation of Salient Closed Contours from Real Images

S. Mahamud, K.K. Thornber and L.R. Williams,

IEEE International Conference on Computer Vision (ICCV) ,

Korfu, Greece, September 1999.

Segmentation of Multiple Salient Closed Contours from Real Images

Shyjan Mahamud, Lance R. Williams, Karvel K. Thornber and Kanglin Xu,

IEEE Trans. on Pattern Analysis and Machine Intelligence ,

Vol. 25(4), April 2003.


http://www.niftyadmin.cn/n/1843884.html

相关文章

HTML5 进阶系列:canvas 动态图表

canvas 强大的功能让它成为了 HTML5 中非常重要的部分,至于它是什么,这里就不需要我多作介绍了。而可视化图表,则是 canvas 强大功能的表现之一。现在已经有了很多成熟的图表插件都是用 canvas 实现的,Chart.js、ECharts等可以制作…

C++STL getline函数

C中有两个getline函数&#xff0c;这两个函数分别定义在不同的头文件中。 1.getline()是定义在<string>中的一个行数&#xff0c;用于输入一行string&#xff0c;以enter结束。 函数原型&#xff1a;getline(cin,str); cin:istream类的输入流对象 str:待输入的string对象…

Denosing Autoencoder原理以及结果简介

本文是看了&#xff0c;bengio的论文Extracting and composing robust features with denoisingautoencoders&#xff0c;整理而得。 文章开始先提出什么是好的特征&#xff0c;或者好的特征应该具有的性质&#xff1a; 1最大化的保留原始信息&#xff0c; 2稀疏性 3 鲁棒性…

jupyter notebook远程配置

一、直接启用 path/to/jupyter-notebook --ip0.0.0.0 --port1234 --no-browser --notebook-dir/home/hx133330/work/jupyter/二、配置启用 1 配置 vim ~/.jupyter/jupyter_notebook_config.py#!/usr/bin/python #*********************************************************…

Denosing Autoencoder训练过程代码详解

普通deep autoencoder训练过程 本文主要参考Deeplearn toolbox中代码 matlab的Deep Learning toolbox&#xff0c;见&#xff1a;https://github.com/rasmusbergpalm/DeepLearnToolbox 一&#xff1a;加载数据 二&#xff1a;pre_training阶段 2.1初始化DAE网络框架 sae sae…

关于C++字符串转换成整数

这里主要利用auoi函数&#xff0c;实例代码如下&#xff1a; #include <iostream> #include <cstdio> #include <cstring> #include <string> #include <queue> #include <map> #include <cstdlib> using namespace std; string for…

显著性轮廓提取、轮廓编组综述要看的内容(三)Tensor Voting学派

Tensor Voting学派 Grard Medioni 这个也是大牛了&#xff0c;在Microsoft Academic上索引数量达到3559。 83年南加州大学博士毕业&#xff0c;现在是南加州大学计算机与工程学院教授&#xff0c;01-07年是南加州大学计算机学院的Chairman。 他 是Tensor Voting方法的始祖&…

Map.putAll()用法

import Java.util.HashMap; public class Map_putAllTest {public static void main(String[] args){ //两个map具有不同的key HashMap map1new HashMap(); map1.put("1", "A"); HashMap map2 new HashMap(); map2.put("2", "…