As this is a coding issue, it has to be done by yourself. You will need to add some logic to only display the biggest detected face. An idea from our end is to compare all the face rectangles detected and only display the biggest one. This means that the biggest rectangle is the closest face to the camera.
Hello Mauricio R.
I had the same idea! I'm only a beginner trying to work my way around Open Vino. Thank you for indulging my question!
I also have another issue, I cannot run my application in GPU. It always return an error: [ ERROR ] ..\thirdparty\clDNN\src\gpu\convolution_gpu.cpp at line: 210
Error has occured for: convolution:conv1
Best_kernel.empty()(true) should be false
Cannot find a proper kernel with these arguments
Thank you for your response.
To continue with your GPU issue, please provide us additional information to replicate your issue from our end.
Which version of OpenVINO are you using?
Which GPU are you using?
What OS are you using?
Which model are you using?
Are you using one of our sample/demo applications?
If you converted the model using the model optimizer, can you provide us your Model Optimizer command?