manef's profile - activity

thanks @berak for your answear. i got that problem but a big problem is that the Loading the trained SVM RBF don't work

problem while load trained svm android hello guys, i'm working on regions detection, so i'm using SVM with opencv 3.4 on

hello guys, i'm working on regions detection, so i'm using SVM with opencv 3.4 on Android studio, i tried to save the trained model of SVM and loaded after but for some reasons that i don't know the load function didn't work in my case ( I'm using Blue stack 4 emulator connected to android studio).The SVM is working fine if i trained him each time ( without using save and load), in my code i used the "getAbsolutePath()" function to get the xml file path and give it to the load function but it don't works. the problem is in the opencv android or in my code please help

SVM svm = SVM.create();
svm.setType(SVM.C_SVC);
svm.setKernel(SVM.RBF);
svm.setC(10000);
svm.setGamma(0.00001);
svm.setTermCriteria(new TermCriteria(TermCriteria.MAX_ITER, 100, 1e-6));
svm.train(trainingDataMat, ROW_SAMPLE, labelsMat);

File datasetFile = new File(Environment.getExternalStorageDirectory(), "dataset.xml");
svm.save(datasetFile.getAbsolutePath());

for loading the trained SVM i used this lines of code

 SVM svm = SVM.create();
 String path = "/storage/emulated/0/dataset.xml";
 svm.load(path());

thanks it worked, the problem was that i created the SVM using SVM.ceate() and then load my XML file. @berak instead of

problem while load trained svm android hello guys, i'm working on regions detection, so i'm using SVM with opencv 3.4 on

I'm trying tio traing SVM , SVM always give my positive result, i tried to change somme param like using RGB with differ

hi @break, in training could i find a function or method to know if my training could give me good result or do i have t

@break i verified that the svm is trained but the problem in the save function link text

mate did you fixed this problem ? i have the same issue and as you SVM is trained but the problem in saving.

SVM training problem while training SVM classifier i got this error while saving the result : OpenCV Error: Parsing erro

the value returned for train ? how and what's is suppose to be like ?! sorry but i have no ideaaa

ow i changed the trainingDataMat from Mat trainingDataMat (47, 27000, CV_32FC1) to only Mat trainingDataMat and it worke

ow i changed the trainingDataMat from Mat trainingDataMat (47, 27000, CV_32FC1) to only Mat trainingDataMat and it worke

this is my first time with reshape and i know that reshape transform my Mat (1350,20) in my case to one row in other Ma

'm using the push_back(reshape(1,1)) to put all my features ( from files) in the same Mat, i looked in many tuto and i f

i changed the Labels Mat to integer and nothing i still have the same error. i have question, the training Mat and the L

memory exception while training SVM to train SVM classifier i use features extracted from different images ( each image

@break I'm going to fill the trainData in my case with features extracted. but the cols of the trainData (is the number

yeah i know but the problem i can't use him with java (android-studio) :( shame .

and the eval function return the performznce of the training ?! and i'm going to use the features extracted for the trai

and the eval function return the performznce of the training ?!

and for adding the features in the Mat of training data i have a question, each image have different number of features

@break and the optic disk is going to be deleted from the result after classification

bu the way how long it takes you to write all this code !! i'm trying to understand it ;)

in each xml file there's 4 image cause the database contain 3 type of lesions of diabetic retinopathy : exudate, Haemorr

for your question about the groundtruth. if you download the data Base you will find the image of the groundtruth png ty

using features extracted with SVM classifier I'm developing a paper. in this paper i had to extract (20 features for eac

this file contain my features extraction from each image . So i for each image i apply some preprocessing treatment and

@break i found a good tuto of using SVM tuto but i can't find how to use my features extracted in the training + i found

@break sorry for wasting your time but in the training of the SVM. the training Data i have to give to the SVM the imag

i had some issue i fixed them and I'm back + i have a professor that want to develop all the paper function in a mobile

I found this answer it's your i think i'll try to correct my code using it answer

thanks for your replays. after applying the SLIC I extract the features so I have to give the classifier the images afte

thanks for your replays. after applying the SLIC I extract the features so I have to give the classifier the images afte

reshape problem while training I want to train my classifier LDA. I followed this link. but my code is crushing with mem

@break sorry for this question but in my groundtruth i have images with value 00 or 255 . I have to change my graound tr

see this link could help

yeah i'm looking to find if there is sign of DR in the image (exudates in my case). so the result of the classification

sure : link

@break please i want to repeat the training process 10 time. It's possible to put the training code in loop 10 time or h

yeah because I'm new in opencv andm dealing with classification for the first time sorry. so i have to put all images of

@break trainLabels it's my groundtruth ? that's mean if that pixel belong to the ROI pixels ? 1 or 0 ?! because i'm wor

i saw this example before but i couldn't understand do i have to resize all my image ? and for the trainig i have to put

LDA training opencv c++ I'm working with retinal images and i' have to use LDA classifier with 2 classes. I have a data

saving image using emulator I'm using android studio with opencv3.4.0, i'm looking to save image after applying some fun

it worked thanks a lot, the problem was in the Lab.add(0,L); as you said it reference so I don't need to add it, if i a

I'm using opencv 3.4.0 and android-studio, I want to apply CLAHE on the L channel so i used the Lab color space, but after applying CLAHE on th L channel i and last i converted the image back to RGB color space but i got this error whil trying to display the image. this is the error :

CvException [org.opencv.core.CvException: cv::Exception: OpenCV(3.4.0-dev) ../../modules/imgproc/src/color.cpp:11207: error: (-215) scn == 3 && (dcn == 3 || dcn == 4) &&



L = new Mat(newImage.rows(), newImage.cols(), CvType.CV_8UC(1));
a = new Mat(newImage.rows(), newImage.cols(), CvType.CV_8UC(1));
b = new Mat(newImage.rows(), newImage.cols(), CvType.CV_8UC(1));

BGR_RGB = Utils.loadResource(getApplicationContext(), R.drawable.retinalimage, CvType.CV_32FC3); 
Imgproc.cvtColor(BGR_RGB, newImage, Imgproc.COLOR_BGR2RGB);
Imgproc.cvtColor(newImage,newImage,Imgproc.COLOR_RGB2Lab);
split(newImage,Lab);
L = Lab.get(0);
a = Lab.get(1);
b = Lab.get(2);

CLAHE ce = Imgproc.createCLAHE();
ce.setClipLimit(2);
ce.setTilesGridSize(new Size(8, 8));
ce.apply(L, L);

Lab.add(0,L);
Core.merge(Lab,newImage);
Imgproc.cvtColor(newImage,newImage,Imgproc.COLOR_Lab2RGB);
showImage(newImage);