Schinkenbrot's profile - activity

• how large are those images ? My training set uses 146 images with 250x250

• "Is it possible to clear the memory?" I thought there is something like a memory cache which I could clear and solve the problem. I have no idea haha :D

• are you able to debug it ? (it will take even longer, but at least you'll get some hint, at which point it fails) I fails at model->train .... in inline Mat asRowMatrix ... at src.getMat(i).clone().reshape(1,1).convertTo(xi, rtype, alpha, beta);

I have no clue :(

I think I simply run out of memory. I decreased the solution of the images (282) and the training worked. After that, I wanted to train my old training set with a lower solution (114 images) but that failed (same error as above). Now nothing works! Even to start my application takes forever. Is it possible to clear the memory? Or what could I do? (Sorry if that is a stupid question, but I am not a programmer and never had such problems) I work with Visual Studio 2013

Hi! Are there limitations for de size of the training set? When I want to train a bigger training set, I obtain this error :

System.Runtime.InteropServices.SEHException msvcr120d.dll!_CxxThrowException(void * pExceptionObject, const _s__ThrowInfo * pThrowInfo) Zeile 154 C++

I am also not able to load an previous created Eigenface- Recognizer with another Trainingset ( //model->load("face-rec-model-eigen.xml"); ) . Same error. That´s strange because it works with my Fisherface-Recognizer.

I have no idea what´s wrong. Thanks for your help.

Thanks but I have already included core.hpp but itsn´t working. That is so strange..

Hi!

I have a problem with the LDA class. I want to use something like this:

cv::Mat projection = LDA::subspaceProject(eigenvectors, averageFaceRow, img_new.reshape(1,1));  
cv::Mat reconstructionRow = LDA::subspaceReconstruct(eigenvectors,averageFaceRow, projection);

But I obtain errors like : LDA is not a namespace or class and subspaceProject identifier not found (same for Reconstruct) I have this code from " Mastering OpenCV with Practical Computer Vision Projects" which works with OpenCV 2.4. I work with OpenCV 3.0 master_contrib extra modules from Github/Itseez

Couldn´t find information about what I need to include or what´s wrong.

Thanks.

Hey I worked through the tutorial "Build opencv_contrib with dnn module" (http://docs.opencv.org/3.1.0/de/d25/t...). to build opencv with the contrib files . But when I build the OpenCV.sln I get errors :

error LNK1104: cannot open file ....\lib\Debug\opencv_bioinspired310d.lib What did I do wrong?

Thanks for your help!

Hi! I want to do face recognition with OpenCV and C++. I am very new to this topic. I read through more tutorials (including http://docs.opencv.org/3.0-beta/modul...) and in every code they include "face.hpp", but my OpenCV 3.0 doesn´t have this file. Where can I get this include file?

Thanks for your help!

Oh my God. It works with the conversion... Thanks thanks thanks! You saved my day :D I will keep your warning in my mind ;)

Yes. I have to create a nice GUI where I can capture images from a webcam, do some transformations, face recognition and then save the new image in any directory... Is it even possible to convert System::String to cv::String?

Hi! I am new to OpenCv and C++.

I word with Visual Studio 2013 and I want save an image with the saveFileDialog or with folderBrowserDialog from windows forms? Is that even possible?

I tried this but I get an error at the line "cv::imwrite(name, image); " : no suitable constructor exists to convert from "System::String^ to cv::String"

 saveFileDialog1->Filter = "JPEG Image|*.jpg|Bitmap Image|*.bmp|Gif Image|*.gif";
             saveFileDialog1->Title = "Save Image";
             saveFileDialog1->ShowDialog(); 

             if (saveFileDialog1->ShowDialog() == System::Windows::Forms::DialogResult::OK){

                String^ name = saveFileDialog1->FileName;
                  cv::imwrite(name, image);
                 MessageBox::Show("Successfully saved");

             }

Any suggestions?
Thanks!