Two salient region detection methods are proposed in this paper: HC AND RC

HC: Histogram based contrast

1. Primary method

It is simply to calculate the saliency of each color in the input image, where each pixel's saliency is defined using its color contrast to all other pixels in the image in L*a*b space:

The above equation can be expanded as,

where N is the number of pixels. Therefore we can conclude that the same color have the same saliency, so saliency value for each color is,

n is the number of distinct pixel colors,  is the probability of the corresponding pixel color in the image I.

2. Speeding up strategy

To reduce the number of colors from 256^3 to 12^3 = 1728, and finally to n = 85 colors in this post.

3. Color space smoothing

In order to reduce noisy saliency results caused by such randomness. We replace the saliency value of each color by the weighted average of the saliency values of similar colors. We choose m = n/4 nearsest colors to refine each color.

See the original paper for the detail of this equation.

RC: Region based contrast

1. Segment the input image into regions using [45](see the original paper)

2. Build the color histogram for each region

3. For a region r_k, we compute its saliency value by measuring its color contrast to all other regions in the image,

where  is the number of pixels of region r_i, designed to emphasize color contrast to bigger regions, and

f(c_k,i) is the probability of the i-th color among all n_k colors in the k-th region, used to emphasize the color differences between dominant colors.

4. Spatially weighted region contrast

We now can incorporate spatial information to the above equation to increase the effects of closer regions and decrease the farther ones.

 is the spatial distance between the two regions. controls the strength of spatial information, the bigger value make less effect of the close regions relatively,  is a spatial prior weighting term similar to center bias.

5. Iteratively segmentation using graph-cut.

Dilation and erosion after each iteration. The region inside the eroded region is set to foreground, and the remaining areas are set to unknown.

However, the (f) is not understood...  ≡(▔﹏▔)≡

CVPR 2011 Global contrast based salient region detection的更多相关文章

  1. Global Contrast based Salient Region Detection (Ming ming Cheng)

    abstract: Automatic estimation of salient object regions across images, without any prior assumption ...

  2. 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 ...

  3. (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 ...

  4. 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 ...

  5. 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 ...

  6. 《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 ...

  7. 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 ...

  8. 《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 ...

  9. 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

  1. STM32是否可以跑linux

    操作系统有两种 用MMU的 和 不用MMU的用MMU的是Windows MacOS Linux Android不用MMU的是FreeRTOS VxWorks ucOS... CPU有两种 带MMU的 ...

  2. C#:生成短网址

    /// <summary> /// 短网址应用 ,例如QQ微博的url.cn http://url.cn/2hytQx /// </summary> /// <param ...

  3. [zz]简单有效,在家就能锻炼!

    简单有效,在家就能锻炼!下面这套动作美腿.美臀.瘦腰,一步到位,是全身塑形的必备,不用多练,每组1分钟.只需一把椅子即可,献给没有时间.条件去健身房的健身爱好者们! http://weibo.com/ ...

  4. C#获取json字符串指定的值

    Newtonsoft.Json在json和对象之间转化是一个非常强大的工具. 对象转化json字符串 Newtonsoft.Json.JsonConvert.SerializeObject() jso ...

  5. linux中如何启动和关闭svn

    1,启动SVN sudo svnserve -d -r /home/data/svn/ 其中 -d 表示守护进程, -r 表示在后台执行 /home/data/svn/  为svn的安装目录 2,关闭 ...

  6. OAF_开发系列10_实现OAF动态LOV设定

    20150712 Created By BaoXinjian

  7. BMP头文件格式以及C语言读取头文件【转】

    BMP头文件格式以及C语言读取头文件[转] (2011-12-24 22:59:17) 转载▼ 标签: 杂谈 分类: 各个领域的知识 BMP图像文件由三部分组成:位图文件头数据结构,它包含BMP图像文 ...

  8. shell条件判断中-a至-z的含义

    [ -a file ] ------- 如果file存在,返回值为真. [ -b file ] ------- 如果file存在且为块特殊文件,返回值为真. [ -c file ] ------- 如 ...

  9. <页面里折合与打开>

    主要思想是:通过覆盖,显示的方式.visible 为 true与false,id以及function函数中参数的不同. 具体代码如下: <script type="text/javas ...

  10. Python多线程互斥锁

    import threading import time num=0 def Mylock(lock): global num lock.acquire() num=num+1 time.sleep( ...