alexander33's profile - activity

thanks for the response.

Thanks a lot for the response, works very fine.

I found the contours of one image that content numbers, then I used boundingrect for find the rectangles of those contours the result is:

I would know how to unite the final contours for then recognize the letters. the result that i want its something like this:

some sugestion for resolve my problem. Thanks"!!!!

I have a data set of images and I want make a threshold of them, for this I’ve been using an adaptive threshold, and morphological operations but there are some images like this example with many blur, some idea for to make the digits as clear as possible. I proved the threshold with OTSU, local threshold and adaptive threshold and the results are not good. My code is

Mat plateFinal = imread(".../plate.bmp", 0);

    Mat medianPlate;
    medianBlur(plateFinal, medianPlate, 3);

    Mat clean_img, clean_open, clean_close;
    adaptiveThreshold(medianPlate, clean_img, 255,
        CV_ADAPTIVE_THRESH_GAUSSIAN_C, THRESH_BINARY_INV, 27, 7); 


    Mat element = getStructuringElement(0, Size(3, 3), Point(1, 1));

    // Apply the morphology operation
    morphologyEx(clean_img, clean_open, MORPH_OPEN, element);
    morphologyEx(clean_open, clean_close, MORPH_CLOSE, element);

    imshow("image clean", clean_close);

and the result is:

I’ve been working with text recognition in a dataset of images, I want segment the characters of the image using components and finding contours of a threshold image. However, many of the characters are united with each other and others components in the image. Some idea for separate ? Thanks for the help!!!! here some examples, and part of my code:

Mat placa_contornos = processContourns(img_placa_adaptativeTreshold_mean);

vector<vector<Point>> contours_placa;


findContours(placa_contornos,
    contours_placa, // a vector of contours
    CV_RETR_EXTERNAL, // retrieve the external contours (REcupera contornos externos)
    CV_CHAIN_APPROX_NONE); // all pixels of each contours


vector<vector<Point> >::iterator itc = contours_placa.begin();
while (itc != contours_placa.end()) {
    //Create bounding rect of object
    Rect mr = boundingRect(Mat(*itc));
    rectangle(imagem_placa_cor, mr, Scalar(0, 255, 0));
    ++itc;
}

imshow("placa con rectangles", imagem_placa_cor);

Works very fine Thanks......

I have a vector of floats and i want insert the element of this vector in the cols of the Mat. reading the doc doc of opencv says that when I pass a vector like parameter in the MAt constructor, The matrix has a single column and the number of rows equal to the number of vector elements. I want just that the matrix has a single row and the numbers of cols equal to the number of vector elements.

vector<float> descriptorsValues;
Mat fm = Mat(descriptorsValues);

thanks for the help !!!!!!

the way like you create the SVM is wrong. since opencv 3.0 changed.

You can see this: http://docs.opencv.org/3.1.0/d1/d73/t... for see one example.

Ptr<SVM> svm = SVM::create();

also i find this explanation, the best that i found. https://www.simplicity.be/article/rec...

good luck!

Thank you, @LBerger, works very fine.....

I have the next image.

I used the function connectedComponentsWithStats for find the components of the image. now i want draw only the components with an area > 3000, in this case there are 3 of the 5 components that the function found, i used the function "compare" for draw the 3 components but the result is not expected (only draw 1 component), Some idea for get the final result? thank you. my result is:

int main(int argc, const char** argv)

{

img = imread("blob.png", 0);

if (img.empty())
{
    cout << "Could not read input image file: " << endl;
    return -1;
}

namedWindow("Image", 1);
imshow("Image", img);

Mat labelImage(img.size(), CV_32S);
Mat stats, centroids;
int nLabels = connectedComponentsWithStats(img, labelImage, stats, centroids, 8, CV_32S);
std::vector<Vec3b> colors(nLabels);
std::vector<int> labels_finals;
colors[0] = Vec3b(0, 0, 0);//background


for (int label = 1; label < nLabels; ++label){ //label  0 is the background
    if ((stats.at<int>(label, CC_STAT_AREA)) > 3000){
        labels_finals.push_back(label);
        //cout << "hola" << endl;
    }

    cout << "area del component: " << label << "-> " << stats.at<int>(label, CC_STAT_AREA) << endl;
    //colors[label] = Vec3b((rand() & 255), (rand() & 255), (rand() & 255));
    colors[label] = Vec3b(0, 255, 0);
}


Mat dst(img.size(), CV_8UC3);
for (int r = 0; r < dst.rows; ++r){
    for (int c = 0; c < dst.cols; ++c){

        int label = labelImage.at<int>(r, c);
        //cout << "label:  " << label << endl; 
        Vec3b &pixel = dst.at<Vec3b>(r, c);//accesa al elemento 
        pixel = colors[label];
    }
}

Mat dst2(img.size(), CV_8UC3);

for (int i = 0; i < labels_finals.size(); ++i){
    std::cout << "path i:  " << labels_finals[i] << ' ' << endl;
    compare(labelImage, labels_finals[i], dst2, CMP_EQ);
}

imshow("compare imagem ", dst2);

}

I have the image:

I used the function connectedComponentsWithStats for find the components of the image. now i want draw only the components with an area > 3000, in this case there are 3 of the 5 components that the function found, i used the function "compare" for draw the 3 components but the result is not expected (only draw 1 component), Some idea for get the final result? thank you. my result is:

and my code is:

int main(int argc, const char** argv)

{

img = imread("blob.png", 0);

if (img.empty())
{
    cout << "Could not read input image file: " << endl;
    return -1;
}

namedWindow("Image", 1);
imshow("Image", img);

Mat labelImage(img.size(), CV_32S);
Mat stats, centroids;
int nLabels = connectedComponentsWithStats(img, labelImage, stats, centroids, 8, CV_32S);
std::vector<Vec3b> colors(nLabels);
std::vector<int> labels_finals;
colors[0] = Vec3b(0, 0, 0);//background


for (int label = 1; label < nLabels; ++label){ //label  0 is the background
    if ((stats.at<int>(label, CC_STAT_AREA)) > 3000){
        labels_finals.push_back(label);
        //cout << "hola" << endl;
    }

    cout << "area del component: " << label << "-> " << stats.at<int>(label, CC_STAT_AREA) << endl;
    //colors[label] = Vec3b((rand() & 255), (rand() & 255), (rand() & 255));
    colors[label] = Vec3b(0, 255, 0);
}


Mat dst(img.size(), CV_8UC3);
for (int r = 0; r < dst.rows; ++r){
    for (int c = 0; c < dst.cols; ++c){

        int label = labelImage.at<int>(r, c);
        //cout << "label:  " << label << endl; 
        Vec3b &pixel = dst.at<Vec3b>(r, c);//accesa al elemento 
        pixel = colors[label];
    }
}

Mat dst2(img.size(), CV_8UC3);

for (int i = 0; i < labels_finals.size(); ++i){
    std::cout << "path i:  " << labels_finals[i] << ' ' << endl;
    compare(labelImage, labels_finals[i], dst2, CMP_EQ);
}

imshow("compare imagem ", dst2);

}

thanks

I have the image:

I used the function connectedComponentsWithStats for find the components of the image. now i want draw only the components with an area > 3000, in this case there are 3 of the 5 components that the function found, i used the function "compare" for draw the 3 components but the result is not expected (only draw 1 component), Some idea for get the final result? thank you. my result is:

and my code is:

int main(int argc, const char** argv)

{

img = imread("blob.png", 0);

if (img.empty())
{
    cout << "Could not read input image file: " << endl;
    return -1;
}

namedWindow("Image", 1);
imshow("Image", img);

Mat labelImage(img.size(), CV_32S);
Mat stats, centroids;
int nLabels = connectedComponentsWithStats(img, labelImage, stats, centroids, 8, CV_32S);
std::vector<Vec3b> colors(nLabels);
std::vector<int> labels_finals;
colors[0] = Vec3b(0, 0, 0);//background


for (int label = 1; label < nLabels; ++label){ //label  0 is the background
    if ((stats.at<int>(label, CC_STAT_AREA)) > 3000){
        labels_finals.push_back(label);
        //cout << "hola" << endl;
    }

    cout << "area del component: " << label << "-> " << stats.at<int>(label, CC_STAT_AREA) << endl;
    //colors[label] = Vec3b((rand() & 255), (rand() & 255), (rand() & 255));
    colors[label] = Vec3b(0, 255, 0);
}


Mat dst(img.size(), CV_8UC3);
for (int r = 0; r < dst.rows; ++r){
    for (int c = 0; c < dst.cols; ++c){

        int label = labelImage.at<int>(r, c);
        //cout << "label:  " << label << endl; 
        Vec3b &pixel = dst.at<Vec3b>(r, c);//accesa al elemento 
        pixel = colors[label];
    }
}

Mat dst2(img.size(), CV_8UC3);

for (int i = 0; i < labels_finals.size(); ++i){
    std::cout << "path i:  " << labels_finals[i] << ' ' << endl;
    compare(labelImage, labels_finals[i], dst2, CMP_EQ);
}

imshow("compare imagem ", dst2);

}

thanks