Human face, emotions and voice recognition.

Question

I am looking for a good method for recognizing faces, emotions and voices in C# . For face recognition, I used to use Emgu CV, which is not accurate, and the performance is very low in low light conditions. I also need to find the emotions of the user. Sadly or happily. But I found it difficult with Emgu CV.

Also for speech recognition I can’t find a solution yet, I found speech recognition, but that’s not what I need.

I do not want to use any online APIs. Can someone offer me any SDKs or Algorithms with which I realize face, emotion and voice recognition?

Answer 1

Face recognition

• Here you can familiarize yourself with the introductory pdf, in particular, take a look at the links for more details.
• Here you can find a good training and demo program with free source code for performing face recognition and face recognition in real time from a webcam (also in OpenCV).
• Eigenface and Face Recognition Home Page .
• You can download CSU Face Identification Assessment System version 5.1 .
• Some articles on face detection .
• From the code project: Detection and recognition of several faces in real time - Detection of faces in the C ++ library with the analysis of skins and movements - Recognition of faces in C # - Detection of faces and eyes using OpenCV .
  

Voice recognition

Just take a look at System.Speech.Recognition Namespace (see this and this ).

Answer 2

It seems you need Kinect. http://www.microsoft.com/en-us/kinectforwindows/develop/

Answer 3

I understand that the question is very old, although I would like to contribute to it, since I am also working on a similar application

There are many available for recognizing faces, emotions and voices now, find below some parameters

1) Face recognition and recognition using OpenCV: http://ahmedopeyemi.com/main/face-detection-and-recognition-in-c-using-emgucv-3-0-opencv-wrapper-part-1/

Pro: open source, so mostly free. You can change the code to suit your needs. Multiple platforms supported.

Con: Accuracy is acceptable, but not great. This can be solved by modifying the library to suit your needs.

2) Face recognition and emotion recognition: try the Microsoft Cognition Service API

Pro: very accurate. It includes many other services, such as NLP, speech to text, text to speech, computer vision, RT language translator, etc. The accuracy is great because the services are hosted on the cloud and are trained for each data entry.

Con: Paid solution. A bit expensive. You must pay for each service separately.

3) Speech recognition: Google Voice Pro API: similar to serving MS. Accuracy is better in noise. con: Paid. It may not be good for one commercial commercial product

4) Speech recognition and NLP: wit.ai/api.ai Pro: Free. Can use data from other public applications. Accuracy is good. Con: I do not find any

Try a few more links as follows. May help a bit.

Security system based on the MS Face API https://www.hackster.io/peejster/facial-recognition-security-system-c6ca6c