Global Contrast based Salient Region Detection (Ming ming Cheng)
abstract:
Automatic estimation of salient object regions across images, without any prior assumption or knowledge of the contents of the corresponding scenes, enhances many computer vision and computer graphics applications. We introduce a regional contrast based salient
object extraction algorithm, which simultaneously evaluates global contrast differences and spatial weighted coherence scores. The proposed algorithm is simple, efficient, naturally multi-scale, and produces full-resolution, high-quality saliency maps. These
saliency maps are further used to initialize a novel iterative version of GrabCut for high quality salient object segmentation. We extensively evaluated our algorithm using traditional salient object detection datasets, as well as a more challenging Internet
image dataset. Our experimental results demonstrate that our algorithm consistently outperforms existing salient object detection and segmentation methods, yielding higher precision and better recall rates. We also show that our algorithm can be used to efficiently
extract salient object masks from Internet images, enabling effective sketch-based image retrieval (SBIR) via simple shape comparisons. Despite such noisy internet images, where the saliency regions are ambiguous, our saliency guided image retrieval achieves
a superior retrieval rate compared with state-of-the-art SBIR methods, and additionally provides important target object region information.
(1)HC:基于直方图对照度的方法,每个像素的显著性值是由它与图像中全部其它像素的颜色差异来确定的,得到全分辨率显著性图像;
(2)RC:基于局部对照度的方法。先将图像切割成小区域。採用的切割方法是基于图的切割,基本切割思想是将每个像素点作为无向图的顶点,两个像素点之间的不相似度作为边的权重。要求连接同样区域内的两个顶点的边的最大权重要小于连接不同区域的变得最小权重,在迭代过程中进行顶点归纳与区域合并,每个区域的显著性值由它与其他全部区域的空间距离和区域像素数加权的颜色差异来确定;空间距离为两个区域重心的欧式距离。较远的区域分配较小的权值。
(3)加速细节:
1、将每一个颜色通道由256个颜色值量化到12个颜色值后,对输入颜色图像计算颜色直方图。保留高频颜色,剩下的颜色舍弃。用直方图中 距离近期的颜色取代。
2、颜色空间平滑:减小量化误差。每一个颜色的显著性值被替换为相似颜色显著性的加权平均。在RGB空间进行量化。用Lab空间度量距离。
接下来会进行代码解析。
详细内容參考:点击打开链接
版权声明:本文博客原创文章,博客,未经同意,不得转载。
Global Contrast based Salient Region Detection (Ming ming Cheng)的更多相关文章
- CVPR 2011 Global contrast based salient region detection
Two salient region detection methods are proposed in this paper: HC AND RC HC: Histogram based contr ...
- Frequency-tuned Salient Region Detection MATLAB代码出错修改方法
论文:Frequency-tuned Salient Region Detection.CVPR.2009 MATLAB代码运行出错如下: Error using makecform>parse ...
- (不断更新)关于显著性检测的调研-Salient Object Detection: A Survey
<Salient Object Detection: A Survey>作者:Ali Borji.Ming-Ming Cheng.Huaizu Jiang and Jia Li 基本按照文 ...
- Minimum Barrier Salient Object Detection at 80 FPS 论文阅读笔记
v\:* {behavior:url(#default#VML);} o\:* {behavior:url(#default#VML);} w\:* {behavior:url(#default#VM ...
- 基于预计算的全局光照(Global Illumination Based On Precomputation)
目录 基于图像的光照(Image Based Lighting,IBL) The Split Sum Approximation 过滤环境贴图 预计算BRDF积分 预计算辐射度传输(Precomput ...
- 《Stereo R-CNN based 3D Object Detection for Autonomous Driving》论文解读
论文链接:https://arxiv.org/pdf/1902.09738v2.pdf 这两个月忙着做实验 博客都有些荒废了,写篇用于3D检测的论文解读吧,有理解错误的地方,烦请有心人指正). 博客原 ...
- 基于屏幕空间的实时全局光照(Real-time Global Illumination Based On Screen Space)
目录 Reflective Shadow Maps(RSM) RSM 的重要性采样 RSM 的应用与缺陷 Screen Space Ambient Occulsion(SSAO) SSAO Blur ...
- 《Benign and maligenant breast tumors classification based on region growing and CNN segmentation》翻译阅读与理解
注明:本人英语水平有限,翻译不当之处,请以英文原版为准,不喜勿喷,另,本文翻译只限于学术交流,不涉及任何版权问题,若有不当侵权或其他任何除学术交流之外的问题,请留言本人,本人立刻删除,谢谢!! 另:欢 ...
- 目标检测之显著区域检测---国外的一个图像显著区域检测代码及其效果图 saliency region detection
先看几张效果图吧 效果图: 可以直接测试的代码: 头文件: // Saliency.h: interface for the Saliency class.////////////////////// ...
随机推荐
- 【42.86%】【Codeforces Round #380D】Sea Battle
time limit per test1 second memory limit per test256 megabytes inputstandard input outputstandard ou ...
- HDU 1013 Digital Roots 题解
Problem Description The digital root of a positive integer is found by summing the digits of the int ...
- Gora快速入门 分类: C_OHTERS 2015-01-30 09:55 465人阅读 评论(0) 收藏
概述 Gora是apache的一个开源项目. The Apache Gora open source framework provides an in-memory data model and pe ...
- ccpc2016长春站打铁记(后记)
Day3 "学术交流日" 自己进我的空间看吧. http://user.qzone.qq.com/190741511/4
- Linux 网络编程系列教程
一.基础理论篇 01.网络协议入门 02.LAN.WAN.WLAN.VLAN 和 VPN 的区别 03.IP 地址介绍 04.广播地址介绍 05.无连接和面向连接协议的区别 06.因特网的IP协议是不 ...
- string与QString之间的转换(两种方法:fromStdString直接转换,或者fromLocal8Bit(cstr.c_str())
string str;QString qstr; //从QString 到 std::stringstr = qstr.toStdString(); //从std::string 到QStringqs ...
- Mysql存储过程中使用cursor
一.表 学生表 CREATE TABLE `t_student` ( `stuNum` int(11) NOT NULL auto_increment, `stuName` varchar ...
- asp.net core2.1 部署centos7/linux系统 -- 安装部署(一)
原文:asp.net core2.1 部署centos7/linux系统 -- 安装部署(一) 1.安装dotnet sdk(添加产品秘钥与yum源) 添加yum源:sudo rpm -Uvh htt ...
- .net core 下的分布式事务锁
原文:.net core 下的分布式事务锁 目录 系统分布式锁的用法 锁的实现 锁的使用 API内的范例: 引用链接 系统分布式锁的用法 公司框架新增功能分布式锁: 锁的性能之王: 缓存 > Z ...
- matlab 运行 AlexNet
0. alexnet 工具箱下载 下载地址:Neural Network Toolbox(TM) Model for AlexNet Network 需要先注册(十分简单),登陆,下载: 下载完成之后 ...