- c - 在位数组中找到第一个零
- linux - Unix 显示有关匹配两种模式之一的文件的信息
- 正则表达式替换多个文件
- linux - 隐藏来自 xtrace 的命令
我需要检测图像中的文本..
这里有一些在大多数情况下都有效的代码..但不是在所有情况下..请参阅附加的输入/输出图像
#include "string"
#include "fstream"
#include "/var/bin/opencv/include/opencv2/opencv.hpp"
using namespace std;
using namespace cv;
void detect_text(string input){
Mat large = imread(input);
Mat rgb;
// downsample and use it for processing
pyrDown(large, rgb);
Mat small;
cvtColor(rgb, small, CV_BGR2GRAY);
// morphological gradient
Mat grad;
Mat morphKernel = getStructuringElement(MORPH_ELLIPSE, Size(3, 3));
morphologyEx(small, grad, MORPH_GRADIENT, morphKernel);
// binarize
Mat bw;
threshold(grad, bw, 0.0, 255.0, THRESH_BINARY | THRESH_OTSU);
// connect horizontally oriented regions
Mat connected;
morphKernel = getStructuringElement(MORPH_RECT, Size(9, 1));
morphologyEx(bw, connected, MORPH_CLOSE, morphKernel);
// find contours
Mat mask = Mat::zeros(bw.size(), CV_8UC1);
vector<vector<Point> > contours;
vector<Vec4i> hierarchy;
findContours(connected, contours, hierarchy, CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE, Point(0, 0));
// filter contours
for(int idx = 0; idx >= 0; idx = hierarchy[idx][0]){
Rect rect = boundingRect(contours[idx]);
Mat maskROI(mask, rect);
maskROI = Scalar(0, 0, 0);
// fill the contour
drawContours(mask, contours, idx, Scalar(255, 255, 255), CV_FILLED);
// ratio of non-zero pixels in the filled region
double r = (double)countNonZero(maskROI) / (rect.width * rect.height);
// assume at least 45% of the area is filled if it contains text
if (r > 0.45 &&
(rect.height > 8 && rect.width > 8) // constraints on region size
// these two conditions alone are not very robust. better to use something
//like the number of significant peaks in a horizontal projection as a third condition
){
rectangle(rgb, rect, Scalar(0, 255, 0), 2);
}
}
imwrite(string("test_text_contours.jpg"), rgb);
}
int main(int argc, char* argv[]){
detect_text(string("input.jpg"));
}
/*
* Compile
* # g++ txtbin.cpp -o txtbin `pkg-config opencv --cflags --libs`
*
* Get opencv version
* # pkg-config --modversion opencv
*
* Run
* # ./txtbin input.jpg output.png
*/
#include "string"
#include "fstream"
#include "/var/bin/opencv/include/opencv2/opencv.hpp"
//#include "/usr/include/opencv2/opencv.hpp"
#include "/usr/include/boost/tuple/tuple.hpp"
using namespace std;
using namespace cv;
using namespace boost;
void CalcBlockMeanVariance(Mat& Img, Mat& Res, float blockSide=21, float contrast=0.01){
/*
* blockSide: set greater for larger fonts in image and vice versa
* contrast: set smaller for lower contrast image
*/
Mat I;
Img.convertTo(I, CV_32FC1);
Res = Mat::zeros(Img.rows / blockSide, Img.cols / blockSide, CV_32FC1);
Mat inpaintmask;
Mat patch;
Mat smallImg;
Scalar m, s;
for(int i = 0; i < Img.rows - blockSide; i += blockSide){
for(int j = 0; j < Img.cols - blockSide; j += blockSide){
patch = I(Range(i, i + blockSide + 1), Range(j, j + blockSide + 1));
meanStdDev(patch, m, s);
if(s[0] > contrast){
Res.at<float>(i / blockSide, j / blockSide) = m[0];
}
else{
Res.at<float>(i / blockSide, j / blockSide) = 0;
}
}
}
resize(I, smallImg, Res.size());
threshold(Res, inpaintmask, 0.02, 1.0, THRESH_BINARY);
Mat inpainted;
smallImg.convertTo(smallImg, CV_8UC1, 255);
inpaintmask.convertTo(inpaintmask, CV_8UC1);
inpaint(smallImg, inpaintmask, inpainted, 5, INPAINT_TELEA);
resize(inpainted, Res, Img.size());
Res.convertTo(Res, CV_32FC1, 1.0 / 255.0);
}
tuple<int, int, int, int> detect_text_box(string input, Mat& res, bool draw_contours=false){
Mat large = imread(input);
bool test_output = false;
int
top = large.rows,
bottom = 0,
left = large.cols,
right = 0;
int
rect_bottom,
rect_right;
Mat rgb;
// downsample and use it for processing
pyrDown(large, rgb);
pyrDown(rgb, rgb);
Mat small;
cvtColor(rgb, small, CV_BGR2GRAY);
// morphological gradient
Mat grad;
Mat morphKernel = getStructuringElement(MORPH_ELLIPSE, Size(3, 3));
morphologyEx(small, grad, MORPH_GRADIENT, morphKernel);
// binarize
Mat bw;
threshold(grad, bw, 0.0, 255.0, THRESH_BINARY | THRESH_OTSU);
// connect horizontally oriented regions
Mat connected;
morphKernel = getStructuringElement(MORPH_RECT, Size(9, 1));
morphologyEx(bw, connected, MORPH_CLOSE, morphKernel);
// find contours
Mat mask = Mat::zeros(bw.size(), CV_8UC1);
vector<vector<Point> > contours;
vector<Vec4i> hierarchy;
findContours(connected, contours, hierarchy, CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE, Point(0, 0));
Scalar color = Scalar(0, 255, 0);
Scalar color2 = Scalar(0, 0, 255);
int thickness = 2;
// filter contours
for(int idx = 0; idx >= 0; idx = hierarchy[idx][0]){
Rect rect = boundingRect(contours[idx]);
Mat maskROI(mask, rect);
maskROI = Scalar(0, 0, 0);
// fill the contour
drawContours(mask, contours, idx, Scalar(255, 255, 255), CV_FILLED);
// ratio of non-zero pixels in the filled region
double r = (double)countNonZero(maskROI) / (rect.width * rect.height);
// assume at least 25% of the area is filled if it contains text
if (r > 0.25 &&
(rect.height > 8 && rect.width > 8) // constraints on region size
// these two conditions alone are not very robust. better to use something
//like the number of significant peaks in a horizontal projection as a third condition
){
if(draw_contours){
rectangle(res, Rect(rect.x * 4, rect.y * 4, rect.width * 4, rect.height * 4), color, thickness);
}
if(test_output){
rectangle(rgb, rect, color, thickness);
}
if(rect.y < top){
top = rect.y;
}
rect_bottom = rect.y + rect.height;
if(rect_bottom > bottom){
bottom = rect_bottom;
}
if(rect.x < left){
left = rect.x;
}
rect_right = rect.x + rect.width;
if(rect_right > right){
right = rect_right;
}
}
}
if(draw_contours){
rectangle(res, Point(left * 4, top * 4), Point(right * 4, bottom * 4), color2, thickness);
}
if(test_output){
rectangle(rgb, Point(left, top), Point(right, bottom), color2, thickness);
imwrite(string("test_text_contours.jpg"), rgb);
}
return make_tuple(left * 4, top * 4, (right - left) * 4, (bottom - top) * 4);
}
int main(int argc, char* argv[]){
string input;
string output = "output.png";
int
width = 0,
height = 0,
blockside = 9;
bool
crop = false,
draw = false;
float margin = 0;
cout << "OpenCV version: " << CV_VERSION << endl;
// Return error if arguments are missing
if(argc < 3){
cerr << "\nUsage: txtbin input [options] output\n\n"
"Options:\n"
"\t-w <number> -- set max width (keeps aspect ratio)\n"
"\t-h <number> -- set max height (keeps aspect ratio)\n"
"\t-c -- crop text content contour\n"
"\t-m <number> -- add margins (number in %)\n"
"\t-b <number> -- set blockside\n"
"\t-d -- draw text content contours (debugging)\n" << endl;
return 1;
}
// Parse arguments
for(int i = 1; i < argc; i++){
if(i == 1){
input = string(argv[i]);
// Return error if input file is invalid
ifstream stream(input.c_str());
if(!stream.good()){
cerr << "Error: Input file is invalid!" << endl;
return 1;
}
}
else if(string(argv[i]) == "-w"){
width = atoi(argv[++i]);
}
else if(string(argv[i]) == "-h"){
height = atoi(argv[++i]);
}
else if(string(argv[i]) == "-c"){
crop = true;
}
else if(string(argv[i]) == "-m"){
margin = atoi(argv[++i]);
}
else if(string(argv[i]) == "-b"){
blockside = atoi(argv[++i]);
}
else if(string(argv[i]) == "-d"){
draw = true;
}
else if(i == argc - 1){
output = string(argv[i]);
}
}
Mat Img = imread(input, CV_LOAD_IMAGE_GRAYSCALE);
Mat res;
Img.convertTo(Img, CV_32FC1, 1.0 / 255.0);
CalcBlockMeanVariance(Img, res, blockside);
res = 1.0 - res;
res = Img + res;
threshold(res, res, 0.85, 1, THRESH_BINARY);
int
txt_x,
txt_y,
txt_width,
txt_height;
if(crop || draw){
tie(txt_x, txt_y, txt_width, txt_height) = detect_text_box(input, res, draw);
}
if(crop){
//res = res(Rect(txt_x, txt_y, txt_width, txt_height)).clone();
res = res(Rect(txt_x, txt_y, txt_width, txt_height));
}
if(margin){
int border = res.cols * margin / 100;
copyMakeBorder(res, res, border, border, border, border, BORDER_CONSTANT, Scalar(255, 255, 255));
}
float
width_input = res.cols,
height_input = res.rows;
bool resized = false;
// Downscale image
if(width > 0 && width_input > width){
float scale = width_input / width;
width_input /= scale;
height_input /= scale;
resized = true;
}
if(height > 0 && height_input > height){
float scale = height_input / height;
width_input /= scale;
height_input /= scale;
resized = true;
}
if(resized){
resize(res, res, Size(round(width_input), round(height_input)));
}
imwrite(output, res * 255);
return 0;
}
最佳答案
您的 detect_text 代码与我的文本检测帖子非常相似 here .如果您使用过该代码,您会看到原始帖子中的输入图像是 1400 x 800。但是您在这篇帖子中的输入图像和您的 previous post通常是四倍大。因此,首先您可以尝试对输入图像进行两次下采样。此外,您的文字看起来有点倾斜,因此您可以尝试旋转矩形而不是直立矩形。然后你可以为你的案例调整参数。正如我在代码中提到的,轮廓过滤标准不是很可靠。对代码进行这些更改后,我得到了如下所示的合理输出。请注意,我用绿色突出显示了检测到的文本区域的旋转矩形。
代码:
void detect_text(string input){
Mat large = imread(input);
Mat rgb;
// downsample and use it for processing
pyrDown(large, rgb);
pyrDown(rgb, rgb);
Mat small;
cvtColor(rgb, small, CV_BGR2GRAY);
// morphological gradient
Mat grad;
Mat morphKernel = getStructuringElement(MORPH_ELLIPSE, Size(3, 3));
morphologyEx(small, grad, MORPH_GRADIENT, morphKernel);
// binarize
Mat bw;
threshold(grad, bw, 0.0, 255.0, THRESH_BINARY | THRESH_OTSU);
// connect horizontally oriented regions
Mat connected;
morphKernel = getStructuringElement(MORPH_RECT, Size(9, 1));
morphologyEx(bw, connected, MORPH_CLOSE, morphKernel);
// find contours
Mat mask = Mat::zeros(bw.size(), CV_8UC1);
vector<vector<Point> > contours;
vector<Vec4i> hierarchy;
findContours(connected, contours, hierarchy, CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE, Point(0, 0));
// filter contours
for(int idx = 0; idx >= 0; idx = hierarchy[idx][0]){
Rect rect = boundingRect(contours[idx]);
Mat maskROI(mask, rect);
maskROI = Scalar(0, 0, 0);
// fill the contour
drawContours(mask, contours, idx, Scalar(255, 255, 255), CV_FILLED);
RotatedRect rrect = minAreaRect(contours[idx]);
double r = (double)countNonZero(maskROI) / (rrect.size.width * rrect.size.height);
Scalar color;
int thickness = 1;
// assume at least 25% of the area is filled if it contains text
if (r > 0.25 &&
(rrect.size.height > 8 && rrect.size.width > 8) // constraints on region size
// these two conditions alone are not very robust. better to use something
//like the number of significant peaks in a horizontal projection as a third condition
){
thickness = 2;
color = Scalar(0, 255, 0);
}
else
{
thickness = 1;
color = Scalar(0, 0, 255);
}
Point2f pts[4];
rrect.points(pts);
for (int i = 0; i < 4; i++)
{
line(rgb, Point((int)pts[i].x, (int)pts[i].y), Point((int)pts[(i+1)%4].x, (int)pts[(i+1)%4].y), color, thickness);
}
}
imwrite("cont.jpg", rgb);
}
关于c++ - 使用opencv检测图像中的文本,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/34415815/
我正在尝试从我的系统中完全删除 opencv。我试图学习 ROS,而在教程中我遇到了一个问题。创建空工作区后,我调用catkin_make 它给出了一个常见错误,我在 answers.ros 中搜索并
我在尝试逐步转移对warpAffine的调用时遇到崩溃(不是异常): void rotateImage( const Mat& source, double degree, Mat& output )
如何处理opencv gpu异常?是否有用于opencvgpu异常处理的特定错误代码集api? 我尝试了很多搜索,但只有1个错误代码,即CV_GpuNotSupported。 请帮帮我。 最佳答案 虽
笔记 我是 OpenCV(或计算机视觉)的新手,所以告诉我搜索查询会很有帮助! 我想问什么 我想编写一个从图片中提取名片的程序。 我能够提取粗略的轮廓,但反射光会变成噪点,我无法提取准确的轮廓。请告诉
我想根据像素的某个阈值将Mono16类型的Mat转换为二进制图像。我尝试使用以下内容: 阈值(img,ret,0.1,1,CV_THRESH_BINARY); 尝试编译时,出现make错误,提示: 错
我对使用GPU加速的OpenCV中的卷积函数有疑问。 使用GPU的卷积速度大约快3.5 运行时: convolve(src_32F, kernel, cresult, false, cbuffer);
我正在尝试使用非对称圆圈网格执行相机校准。 我通常找不到适合CirclesGridFinder的文档,尤其是findHoles()函数的文档。 如果您有关于此功能如何工作以及其参数含义的信息,将不胜感
在计算机上绘图和在 OpenCV 的投影仪上投影之间有什么区别吗? 一种选择是投影显示所有内容的计算机屏幕。但也许也有这样的选择,即在投影仪上精确地绘制和投影图像,仅使用计算机作为计算机器。如果我能做
我将Processing(processing.org)用于需要人脸跟踪的项目。现在的问题是由于for循环,程序将耗尽内存。我想停止循环或至少解决内存不足的问题。这是代码。 import hyperm
我有下面的代码: // Image Processing.cpp : Defines the entry point for the console application. // //Save
我正在为某些项目使用opencv。并有应解决的任务。 任务很简单。我有一张主图片,并且有一个模板,而不是将主图片与模板进行比较。我使用matchTemplate()函数。我只是好奇一下。 在文档中,我
我正在尝试使用以下命令创建级联分类器: haartraining -data haarcascade -vec samples.vec -bg negatives.dat -nstages 20 -n
我试图使用OpenCV检测黑色图像中一组形状的颜色,为此我使用了Canny检测。但是,颜色输出总是返回为黑色。 std::vector > Asteroids::DetectPoints(const
我正在尝试使用OpenCv 2.4.5从边缘查找渐变方向,但是我在使用cvSobel()时遇到问题,以下是错误消息和我的代码。我在某处读到它可能是由于浮点(??)之间的转换,但我不知道如何解决它。有帮
我正在尝试构建循环关闭算法,但是在开始开发之前,我想测试哪种功能描述符在真实数据集上效果更好。 我有两个在两个方向拍摄的走廊图像,一个进入房间,另一个离开同一个房间。因此它们代表相同的场景,但具有2个
有没有一种方法可以比较直方图,但例如要排除白色,因此白色不会影响比较。 最佳答案 白色像素有 饱和度 , S = 0 .因此,在创建直方图时很容易从计数中删除白色像素。请执行下列操作: 从 BGR 转
就像本主题的标题一样,如何在OpenCV中确定图像的特定像素(灰度或彩色)是否饱和(例如,亮度过高)? 先感谢您。 最佳答案 根据定义,饱和像素是指与强度(即灰度值或颜色分量之一)等于255相关联的像
我是OpenCV的新用户,正在从事大学项目。程序会获取输入图像,对其进行综合模糊处理,然后对其进行模糊处理。当对合成模糊图像进行反卷积时,会生成边界伪像,因为...好吧,到目前为止,我还没有实现边界条
我想知道OpenCV是haar特征还是lbp是在多尺度搜索过程中缩放图像还是像论文中提到的那样缩放特征本身? 编辑:事实证明,检测器可以缩放图像,而不是功能。有人知道为什么吗?通过缩放功能可以更快。
我在openCv中使用SVM.train命令(已定义了适当的参数)。接下来,我要使用我的算法进行分类,而不是使用svm.predict。 可能吗?我可以访问训练时生成的支持 vector 吗?如果是这
我是一名优秀的程序员,十分优秀!