搜索资源列表
TextDetect
- 云行TextDetection.exe程序，打开任意一幅bmp文件。点击“操作 检测文本区域”， 变会弹出文本检测的结果框。框内设定显示前六个文本区域的二值化结果，注意该框不要移动。关闭该框，BMP文件原始图像中用红色矩形框显示出检测出的文本区域。-cloud OK TextDetection.exe procedures, arbitrary opened a bmp file. Click on the "operational # 61664 Detection
driverdetection
- 司机疲劳识别程序。调整摄像头光线，拍摄下具有红眼的司机头部照片，与正常拍摄下照片一起处理，判断出司机是否处于疲劳状态。-driver fatigue identification procedures. Adjust light camera to take pictures with red-eye photo of the driver head, and under normal shooting photos together, determine whether the drivers
vcCellRecg
- 本系统是一个医院中血液红细胞计数的实用系统，该系统可以很方便地应用于临床诊断上，大大的提高速度和效率。用vc6实现。-the hospital system is a red cell blood count of usable system, The system can be conveniently applied to the clinical diagnosis and greatly increase the speed and efficiency. Vc6 used to ach
hongxibaoshibie
- 血液红细胞识别系统，基于dephi语言的编程实现的，能够识别血液中红细胞的数量 特征-Blood red blood cell recognition system based on dephi language programming, and to identify the number of red blood cells in the blood characteristics, etc.
shibie
- 基于bp神经网络的车牌识别系统 神经网络部分训练有待提高-The design of intelligent transportation systems for applications such as electronic toll,traffic flow analysis,speed Limit and red light violation enforcement has been attracted an increasing attention from researchers.I
Motion_Detection
- Motion detection results If you double-click the Switch block so that the signal is connected to the SAD side, the Video Viewer block displays the SAD values, which represent the absolute value of the difference between the current and pr
linedetect
- 1拍摄一张包含两本成一定夹角放置的书的图像2获得书的边缘二值图像3通过hough变换在原始灰度图像中用红色标记出书的边缘，计算两本书的夹角-1 shot 1 into a certain angle contains two books placed on the edge of the image 2 receive the binary image 3 by hough transform the original gray image using the red mark the edge
xicheng
- 在google earth中寻找线路 并用红线显示 的KML文件-Line in google earth to find and use the red line shows the KML file
HoughLineTracking
- 从摄影头输入影像，可侦测直线物体，侦测到的直线以红色线条显示出来，以OPENCV的Hough transform实作-The first input from the photographic images, can detect linear objects detected straight lines shown in red to OPENCV the Hough transform implementation
trackingredcolorobjects
- 实现了一个红色图像的跟踪识别，大家一起学习-Implementation of a red image of the track recognition, we will study together
ylh
- 测试方法 1、在你的电脑上建一工作目录； 2、分别将车牌图像和测试程序下载到你建立的工作目录上； 3、解压车牌图像； 4、直接运行测试程序 算法核心 依公式 黄 =（红 + 绿）/ 2 ，灰度 = （黄 + 蓝）/ 2 ， 将红、绿、蓝三种颜色构成的色彩空间映射到由黄、蓝两种颜色构成的色彩空间，进一步取值黑、蓝、灰、黄和白五种， 这包括了车牌识别所需要的车牌色（蓝、黄、白、黑）和字符色（白、黑）， 且灰能保留图像的识别信息，克服二值化阈值缺陷；
LPR_by_ylh
- 依公式 黄 =（红 + 绿）/ 2 ，灰度 = （黄 + 蓝）/ 2 ，将红、绿、蓝三种颜色构成的色彩空间映射到由黄、蓝两种颜色构成的色彩空间，进一步取值黑、蓝、灰、黄和白五种，这包括了车牌识别所需要的车牌色（蓝、黄、白、黑）和字符色（白、黑），且灰能保留图像的识别信息，克服二值化阈值缺陷；基于三值图像的车牌识别包括基于三值图像的字符识别和基于三值图像的按分割反推的车牌定位，是建立在三值图像基础上的创新的车牌识别算法体系。-According to the formula Yellow = (r
Positioning-iris-center
- 采用matlab软件，并用积分投影定位人脸眼睛的红膜中心-Based on matlab software, and integral projection positioning of the red eyes face film center
xibaosedushibie
- 对细胞图像进行色度识别，并计算红色所占图像比例-Cell image chromaticity identify and calculate the proportion of red share images
pattern_recognition
- 根据训练集图像，对目标图像中的八个子目标图像进行识别，用红色矩形将各个子目标图像框起来，并在子目标图像的中央位置，写上对其识别的结果，即子目标图像的名字。-请键入文字或网站地址，或者上传文档。 取消 Gēnjù xùnliàn jí túxiàng, duì mùbiāo túxiàng zhōng de bā gè zǐ mùbiāo túxiàng jìnxíng shìbié, yòng hóngsè jǔxíng jiāng gège zǐ mùbiāo túxiàng kuān
QtTracker3
- 使用開源資源實現圖形處理 紅色球形追蹤(xp)-use qt ide and opencv for image process, use web camera to track red ball on xp system
face-detection
- 实现人脸检测，能将人脸部分用红线框出，为人脸识别做了较好的基础。里面有检测照片。-Implement face detection, can face parts out of the box with a red line for face recognition do a good foundation.There are detected photos.
Moving-multi-object-search-SYSTEM
- 基于USB摄像头的运动目标捕捉系统，在电脑上插上USB摄像头后开启程序，程序可以在视频画面上自动捕捉运动的物体并以红框标注，还会把运动物体的截图存储在电脑上-Moving object based on USB camera capture system on the computer plug in the USB camera after opening procedure, the program can be on the video screen automatically captu