Tarcisioflima's profile - activity

Converting Mat to one dimensional float array for EM? I'm trying to convert a Python code to Java. However, I'm unable t

Did you published the paper?

did you published the paper?

Thank you Greydel. I will take a look on your approach

Thank you Greydel. I will first try to use finding blobs, I just need to figure out about it

How to remove shadows from foreground after segmentation? I am developing an algorithm in Python, which is supposed to i

I'm not using RGB, I was already using just S and V form HSV to train it. I will take a look on Lab color! Thank you

Lightning invariant model? Do you have anything about it?

Kbarni, did you face shadows on your paper? I'm trying to find a way to avoid them

@kbarni Well, I'm not sure about it as I'm retraining it every time. Also, shadows are an issue here.

Expectation Maximization Prediction Issues I was trying to segment a leaf from the background to be able to identify the

@StevenPuttemans I tried some shadow removal technique, but without success.

Detection of leaf on unpredictable background A project I have been working about for some time is a unsupervised leaf s

Detection of leaf on unpredictable background A project I have been working about for some time is a unsupervised leaf s

Detection of leaf on unpredictable background A project I have been working about for some time is a unsupervised leaf s

Detection of leaf on unpredictable background A project I have been working about for some time is a unsupervised leaf s

@pklab do you think it can lead with shadows in leaf segmentation?

Hello, I have found the contours of the object in the image with a cv2.findContours and I want to clip the image in the extreme points. However, the image returned is not correct.

Below is the code, I have implemented. Any hint?

def clipping_image( image ):
    '''
    Clip segmented imaged based on the contours of the leaf
    '''
    image = cv2.cvtColor( image, cv2.COLOR_BGR2GRAY );
    segmented, contours, hierarchy = cv2.findContours(image, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
    cnt = contours[0]
    xmin = min(tuple(cnt[cnt[:, :, 0].argmin()][0]))
    ymin = min(tuple(cnt[cnt[:, :, 1].argmin()][0]))
    xmax = max(tuple(cnt[cnt[:, :, 0].argmax()][0]))
    ymax = max(tuple(cnt[cnt[:, :, 1].argmax()][0]))

    clipped = segmented[xmin:xmax, ymin:ymax]

    return clipped

Thank you

Object Segmentation I begin to develop an algorithm, which has the purpose to identify the area of the leaf that contain

Expectation Maximization OpenCV I begin to develop an algorithm, which has the purpose to identify the area of the leaf

Expectation Maximization OpenCV I begin to develop an algorithm, which has the purpose to identify the area of the leaf

Expectation Maximization OpenCV I begin to develop an algorithm, which has the purpose to identify the area of the leaf

Thank you, berak! It works when changing to: images = [cv2.cvtColor(cv2.imread( filename ), cv2.COLOR_BGR2RGB),image]

Imread wrong output Hi, I'm trying to output one image by using plot; however, it is showing wrong colors as you can see

Imread wrong output Hi, I'm trying to output one image by using plot; however, it is showing wrong colors as you can see

I have build some code in python from that code. However, the results are not the same

Coverting C++ to Python I have the following OpenCV code in c++ and I would like to convert it to python. Do any of you

Expectation Maximization is founding it on the background!

@sjhalayka I cannot control it.

Removal Greenish Shadows from Background I have an image of a leaf on a poorly white screen and need to find out just th

I am using OpenCV EM to segment a image on the HSV domain. Therefore, the segmentation detect some false positives [Highlights in Yellow]. Below, you can see.

Therefore, I tried to use threshold to remove them without success as showing in the described attachment. I got the better result with THRESH_TOZERO_INV; however, I lost part of the leaf.

Any help on how to keep only the Leaf without false positives?

@Kbarnin, I'm trying to use the S and V from HSV domain to train my EM algorithm; however, due to greenish shadows, it i

How to avoid compreesion artifacts on segmentation? I am using OpenCV EM to segment a image on the HSV domain. Therefore

I was able to get the expected results changing my code as below: def clipping_image( image ): ''' Clip segment

I'm trying to implement the below piece of code in JAVA; however, I cannot find a replacement for Vec3f. Any hint on it?

Mat samples( img.rows * img.cols, 3, CV_32FC1 );

int index = 0;
for( int y = 0; y < img.rows; y++ ) {
    Vec3f * row = float_img.ptr(y);
    for( int x = 0; x < img.cols; x++ )
        samples.at<Vec3f>(index++, 0) = row[x];
}
return samples;

Thank you!

How to clip an image by extreme points? Hello, I have found the contours of the object in the image with a cv2.findConto

I added it on the code.

What is the java equivalent? I'm trying to implement the below piece of code in JAVA; however, I cannot find a replaceme

What is the java equivalent? I'm trying to implement the below piece of code in JAVA; however, I cannot find a replaceme

I'm trying to generate a Mat from my RGB image to train EM algorithm. Thus, it is creating a sample vector.

What is the java equivalent? I'm trying to implement the below piece of code in JAVA; however, I cannot find a replaceme

I'm trying to use EM::predict2(sample, probs) to predict if a pixel is part of a leaf or not; however, I'm getting the error:

CvException [org.opencv.core.CvException: cv::Exception: /build/master_pack-android/opencv/modules/ml/src/em.cpp:569: error: (-215) sample.size() == Size(means.cols, 1) in function cv::Vec2d cv::ml::EMImpl::computeProbabilities(const cv::Mat&, cv::Mat*, int) const]

When I'm calling:

Mat probs = new Mat(imgHSV.rows(), em.getClustersNumber(), CvType.CV_32FC1);

Mat mPredict = new Mat(1, 2, CvType.CV_8UC1);
mPredict.put(0,0,imgHSV.get(i,j)[1]);
mPredict.put(0,1,imgHSV.get(i,j)[2]);

double[] probabilities = em.predict2(mPredict, probs);

To clarify some points, I'm showing below the pseudocode that I was trying to follow:

stackedPixels ← ∅
for all pixelRow in image do
    for all pixel in pixelRow do
        stackedPixels ← stackedPixels ∪ pixel
    end for
end for
EM ← OpenCV.EM(nClusters = 2, covMatT ype = OpenCV.DIAGONAL)
EM.train(stackedPixels)
return EM


key ← hash(pixel[S], pixel[V])
if hash in pixelDictionary then
    return pixelDictionary[key]
end if
probabilities ← EM.predict(pixel[S], pixel[V])
pixelDict[key] = probabilities[0] > probabilities[1]
return pixelDict[key]