Description: 完成人脸检测、人眼定位和嘴巴定位.把得到的人脸区域用绿色矩形标注，处理竖直的两条边-Complete face detection, the human eye and mouth positioning positioning. To get face region marked by the green rectangle, deal with the two vertical edges Platform: |
Size: 3262464 |
Author:李旭锋 |
Hits:
Description: 一种快速的多边形和矩形检测算法，可以广泛的应用于各种目标识别领域-A fast polygon and rectangle detection algorithm can be widely used in various areas of target identification Platform: |
Size: 11264 |
Author:chendong |
Hits:
Description: Hough算法检测矩形的长，并给出矩形的四个顶点坐标，极坐标中角度精度为1度。-Hough algorithm Detect long rectangle, and give the four vertices of rectangular coordinates, polar coordinates in the perspective of an accuracy of 1 degree. Platform: |
Size: 363520 |
Author:七禾 |
Hits:
Description: 用于矩形检测的源代码，已配说明，易看懂。但不适合于车牌检测等复杂的矩形检测-Rectangular detection for the source code has been assigned that easy to understand. But not suitable for detection of license plate detection rectangular complex Platform: |
Size: 1024 |
Author:郭宇 |
Hits:
Description: 在opencv中检测一个图像是否有矩形，本程序很实用-An image in opencv detect whether the rectangle, the procedure is very useful Platform: |
Size: 3072 |
Author:HEllO2010 |
Hits:
Description: 使用opencv去掉二值化图像中黑色面积较小的连通域。
程序中语句 tmparea = fabs(cvContourArea(contour)) 可以得到当前连通域的面积，当此面积小于阈值时对其填充为白色。
rect = cvBoundingRect(contour,0) 得到的是框住连通域的最小矩形，对矩形中的黑色部分将其填充为白色，但是这样的话，连通域6和4两个连通域被填充成了白色的矩形，这显然不符合我们的要求，这样就要判断此连通域是黑色联通域还是白色连通域，采用的方法是测试矩形的中心点，如果其为黑色，则认为此连通域是黑色连通域，否则为白色联通域，对于黑色联通域我们对其进行白色填充处理，对于白色联通域则保持不变。-Using opencv binary image to remove the black connected components smaller.
Program statement tmparea = fabs (cvContourArea (contour)) can get the current connected component of the area, when this area is less than the threshold when it filled with white.
rect = cvBoundingRect (contour, 0) get is a box to live in the smallest rectangle connected domains, part of the black rectangle to fill with white, but this is the case, connected components 6 and 4 are filled into two connected components of white rectangle, which obviously does not meet our requirements, so we must determine if the connected domain is black or white Unicom domain connected domain, the approach is to test the center of the rectangle, if it is black, is that the black connected components connected domain, otherwise the domain of white Unicom, China Unicom for the black white fill field we deal with them, for the white Unicom domain remains unchanged.
Platform: |
Size: 1024 |
Author: |
Hits:
Description: 利用opencv测量矩形的C++程序，可以直接检测出矩形，即使背景很复杂-Measured using a rectangle opencv C program, you can directly detect the rectangle, even if the background is very complex Platform: |
Size: 3072 |
Author:azure |
Hits:
Description: 轮廓识别，矩形检测，同时也包含部分基于不变矩的最佳匹配代码-the code used to detect and redraw contours such as rectangle,it also include some code best match based on MCvHuMoments Platform: |
Size: 37888 |
Author:新村 |
Hits:
Description: Aforge.net开发的形状检测，能够自动化检测出图像中的三角形、圆形、矩形等形状-Aforge.net can detect the triangle and rectangle and etc. Platform: |
Size: 711680 |
Author:mafei863 |
Hits:
Description: 简单的检测一幅图像中是否有正方形长方形圆及三角形，一幅图图像中可以有很多图形，但是竖直方向不能重合-Simple detect whether an image of a circle and a square rectangle triangle, a picture can have a lot of graphic images, but can not overlap in the vertical direction Platform: |
Size: 101376 |
Author:zhangle |
Hits:
Description: It is a matlab source code which detect different shape in image and told whether it is circle, rectangle or triangle. in this code i use hough transformation. Platform: |
Size: 10240 |
Author:Ashab Uddin |
Hits:
Description: It is a matlab source code detect all the circle and rectangle in a image and create box on the original image at the position of the circle or ractangle
Platform: |
Size: 4096 |
Author:Ashab Uddin |
Hits:
Description: 是指利用第一次训练的分类器在负样本原图上进行行人检测时所有检测到的矩形框，这些矩形框区域很明显都是误报，把这些误报的矩形框保存为图片，加入到初始的负样本集合中，重新进行SVM的训练，可显著减少误报。这种方法叫做自举法-The first is the use of trained classifier all detected rectangle detect pedestrians in the negative when the sample picture, the rectangular frame are obviously false, to save these false rectangle for the picture, adding to negative in the initial sample collection, re-SVM training, can significantly reduce false positives. This method is called bootstrap method Platform: |
Size: 2048 |
Author:孔祥山 |
Hits:
Description: 本资源运用Matlab中的计算机视觉技术对视频监控中的运动人体的一些异常行为进行研究分析，涉及到了运动目标检测以及跟踪和人体异常行为检测等几个方面。背景模型的建立则是分别利用了中值滤波法和二值化背景模版建模法，通过帧间差分
来实现不断更新背景模版。在检测运动人体异常行为中，本文在检测运动人体跌倒的异常行为时利用外接矩形来确定运动人体及其质心，并通过定义一些特征算子来把人体行为进行量化，从而判断是否行为异常。(In this paper, we use matlab technology to detect abnormal human movement and video resources. The background model is established by using the median filtering method and the binary background template modeling method, through the frame difference
To update the background template constantly. In the detection of abnormal behavior of moving human body, this paper uses the outer rectangle to determine the moving human body and its center of mass, and defines some characteristic operators to quantify the human behavior, so as to determine whether the abnormal behavior.) Platform: |
Size: 21035008 |
Author:沃呦俏豚 |
Hits:
Search - rectangle detect