do you know if the OPENCV integration can detect more than 1 classifier ?
… i’ve sucesful intealled the OPENCV in my HASSIO, and it detects face (few false positives) , full body (not always detecting positives) and upperbody (several positives that are not posite).
My raspeberry PI 3b is collecting the images from 2 old mobiles cameras with streaming service, but it just detects one classifier and not 2 at the same time (face + upperbody)
Have you figured out how everything is done? How can I train the system so that a person’s name can be identified by their face? How and where it should be specified so that the system determines the name of the person, as in the case of deepstack.
Вы разобрались как все делается? Как обучить систему, чтобы по лицу можно было определить имя человека? Как и где это нужно указывать, чтобы система определяла имя лица, как в случае deepstack.
Hi, I’ve moved from OpenCV to Dlib .
on Dlib everything works better and I’m able to identify faces with just one photo for the persons.
At the moment , I’ve also moved fro mRaspberry 3 to the 4 with 4Gb RAM
1) Is it possible to identify faces from different angles?
2) Can I specify multiple photos for one name?
3) Is it possible to use this method for car parking, for example, to specify certain places where we put the car and register the type of parking lot 1, parking lot 2, parking lot 2, etc.?
Можно опознавать лица под разным ракурсом?
Можно для одного имени указать несколько фоток?
Можно ли такой способ использовать для автопарковки, к примеру указать определенные места, куда мы ставим машину и прописать типа парковка 1, парковка 2, парковка 2 и т.д?
Thanks. I installed it and tried it. Yes, the result of dlib face identify did not satisfy me. Deepstack recognizes faces better, but in addition to face recognition, I need to recognize free parking spaces in the parking lot, and OpenCV can handle this.
Спасибо. Я установил и попробовал. Да, результат dlib face identify меня не удовлетворил. Deepstack лучше распознает лица, но мне кроме распознавания лиц нужно распознавать свободные машиноместа на автопарковке, а с этим может справиться OpenCV.
Hi!
I am very new to OpenCV but eager to learn! Been doing Home Assistant for a while now.
My question: Could you please give me an explanation on how you get the pictures you need in the xml files? Do you have a link inside the xml file or is it decoded or something? i am also wondering what kind of xml editor you are using.