add face recognition feature with a given dataset
@unni332265

@unni332265
add a module to detect a human face in a video. try for good performance.make the module self learning so that new faces can be detected and labeled in one step.

hello
can you send me a video to test the project,
i used a video found on the net but i got just this result

E:\peopleTracking\pytracking\Human-detection-and-Tracking-master\Human-detection-and-Tracking-master\videos\v1.mp4*.mp4
[]

Issues should contain the following details which increases the probability of it get resolved quickly

when the any of the face is detected from camera it shows label dynamically changing. like 4,7,22,34,53
so i m not able to understand what are these labels..

looking forward to this.
thanks..

existing license does not seem to be good suggest a new one

I have read your issue #25 , but my problem still persists.

OpenCV(3.4.1) Error: Unspecified error (The node is neither a map nor an empty collection) in cvGetFileNodeByName, file /io/opencv/modules/core/src/persistence_c.cpp, line 753
Traceback (most recent call last):
  File "main.py", line 137, in <module>
    recognizer.read("model.yaml")
cv2.error: OpenCV(3.4.1) /io/opencv/modules/core/src/persistence_c.cpp:753: error: (-2) The node is neither a map nor an empty collection in function cvGetFileNodeByName

This is the error, you mentioned to change line 62,
recognizer.save("cont.yaml") to
recognizer.save("model.yaml")
but this is my line 62
predict_tuple = recognizer.predict(frame_orginal_grayscale)

I am not able to figure out, what's wrong?

Port this repository to python2 from python3

• code should support python2.7 and opencv3.x
• other useful scripts in scripts folder should also be converted to python2
• make a separate branch for python2
• multiple pull requests are allowed for this.

😃

I try to run your project
but it can not be run

So this is an error

$ python3 main.py --videos videos
/Users/teamzoon/Downloads/Human-detection-and-Tracking-master/videos/6.mp4*.mp4
['/Users/teamzoon/Downloads/Human-detection-and-Tracking-master/videos/6.mp4']
(360, 640, 3)
(360, 640, 3)
Traceback (most recent call last):
File "main.py", line 160, in
temp = background_subtraction(previous_frame, frame_resized_grayscale, min_area)
File "main.py", line 118, in background_subtraction
im2, cnts, hierarchy = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
ValueError: not enough values to unpack (expected 3, got 2)

Hi Sir,
core dump occurred when I type the following command
./humandetect ../GEM_time.mp4
opencv_contrib-3.4.1/modules/face/src/facerec.cpp, line 61
terminate called after throwing an instance of 'cv::Exception'
what(): OpenCV(3.4.1) /opencv_contrib-3.4.1/modules/face/src/facerec.cpp:61: error: (-2) File can't be opened for reading! in function read

Aborted (core dumped)

Could you kindly to give a hint about how to solve this issue?

snowuyl

Issues should contain the following details which increases the probability of it get resolved quickly

• Exact error or Issue details
• OpenCV Version
• Python Version
• Operating System
• Changes done, if any in the original code

Issues should contain the following details which increases the probability of it get resolved quickly

• Exact error or Issue details
• OpenCV Version
• Python Version
• Operating System
• Changes done, if any in the original code

OpenCV Error: Unspecified error (The node is neither a map nor an empty collection) in cvGetFileNodeByName, file C:\projects\opencv-python\opencv\modules\core\src\persistence.cpp, line 891
Traceback (most recent call last):
File "main.py", line 137, in
recognizer.read("model.yaml")
cv2.error: C:\projects\opencv-python\opencv\modules\core\src\persistence.cpp:891: error: (-2) The node is neither a map nor an empty collection in function cvGetFileNodeByName

Earlier there was ' recognizer.load("model.yaml") ' in the original code but there is no attribute 'load' attribute in new version of current opencv which has been replaced by 'read'.

Human detection and face detection is pretty slow with using CPU. opencv provides framework for integrating CUDA but there is no native support by opencv. Suggest a way to use CUDA framework with this code. PR are welcome 🛩️ 😄

Port this repo to C++

• code should be written in C++.
• make a separate branch for this.
• functionality should be same and performance should be better.
• useful scripts in scripts folder should also be ported.
• multiple pull requests are allowed for this but make sure that you are on correct path
  😄 😄

Issues should contain the following details which increases the probability of it get resolved quickly

• Exact error or Issue details
• OpenCV Version
• Python Version
• Operating System
• Changes done, if any in the original code

Traceback (most recent call last):
File "main.py", line 5, in
import imutils
ModuleNotFoundError: No module named 'imutils'

Hi, ITCoders,
I want to run this proj to watch the demo, but i found some incompatibilities in opencv3
As I have searched in google, I change two line of your code.
But I still have an error with no idea.

At line 16, I changed it to recognizer = cv2.face.LBPHFaceRecognizer_create()
At line 137, I changed it to recognizer.read("model.yaml")

but still have an error:

Traceback (most recent call last):
File "main.py", line 137, in
recognizer.read("model.yaml")

cv2.error: /home/ssss/opencv/opencv/modules/core/src/persistence.cpp:891: error: (-2) The node is neither a map nor an empty collection in function cvGetFileNodeByName

Can you give me some help ? Thanks !

I have a problem and I can not run my code. I have python 3.6 with opencv 3.4. It seems coding is not compatible with this version so I changed it a little.
At first I had problem with line 16: recognizer = cv2.face.createLBPHFaceRecognizer()
so I changed it into recognizer = cv2.face.LBPHFaceRecognizer_create()

then I had problem with line 137: recognizer.load("model.yaml")
And I changed it again to: recognizer.read("model.yaml")

But now I found the error saying : error: (-2) The node is neither a map nor
an empty collection in function cvGetFileNodeByName

And I have no idea what to do with this.

Both are using same "model.yaml" file and LBPHFaceRecognizer algorithm.

In main.py convert the code to a class and write main function again 🚀 🎧

crop the image of human from video frame (coordinates are being returned by HOG.detectMultiScale method)
@unni332265
hurry!!!

hi, i want to ask what kind of neural network you used in order to detect human or face in your project and how did you train it?

Issues should contain the following details which increases the probability of it get resolved quickly

• Exact error or Issue details
• OpenCV Version
• Python Version
• Operating System
• Changes done, if any in the original code

i do this steps to run the code:

cd to Human-detection-and-Tracking-master
2)python3 main.py /video
i get that error again.
usage: main.py [-h] -v VIDEOS
main.py: error: the following arguments are required: -v/--videos

How do i run this code in realtime camera stream using opencv?

Hi,
I run 'python3 main.py -v video/' and the below error occured:

Traceback (most recent call last):
File "main.py", line 140, in
recognizer.read("model.yaml")
cv2.error: OpenCV(4.1.0) /io/opencv/modules/core/src/persistence.cpp:2046: error: (-215:Assertion failed) isMap() in function 'operator[]'

I wana run the code on ubuntu 16.04 and opencv(4.1) and python 3.5.
what's wrong?

thanks

Issues should contain the following details which increases the probability of it get resolved quickly

• Exact error or Issue details

D:\python\Human-detection-and-Tracking-master>python main.py -v D:\python\Human-detection-and-Tracking-master\videos
D:\python\Human-detection-and-Tracking-master\videos\VID-20181220-WA0006.mp4*.mp4
['D:\\python\\Human-detection-and-Tracking-master\\videos\\VID-20181220-WA0006.mp4']
Traceback (most recent call last):
  File "main.py", line 140, in <module>
    recognizer.read("model.yaml")
cv2.error: OpenCV(4.0.0) C:\projects\opencv-python\opencv\modules\core\src\persistence.cpp:2047: error: (-215:Assertion failed) isMap() in function 'cv::FileNode::operator []'

• OpenCV Version - 4.0
• Python 3.x
  ** Windows 10*
• Changes done, if any in the original code - nope !

Issues should contain the following details which increases the probability of it get resolved quickly

• Exact error or Issue details
• OpenCV Version
• Python Version
• Operating System
• Changes done, if any in the original code

I am getting this error . please anyone help me on this
File "main.py", line 17, in
recognizer = cv2.face.LBPHFaceRecognizer_create()
AttributeError: module 'cv2.cv2' has no attribute 'face'

Issues should contain the following details which increases the probability of it get resolved quickly

i am sorry to bother you .I wanna know how to use usbcamera to run your demo?
i am using opencv3.4.0 python3.4.0
ubantu in jetsontx2

The given link for linux installation of opencv is meant to install opencv for python 2.7 not python3. As a result upon following those instructions import cv2 works in python command line but not for python 3.

Also upon trying to run code using python 2.7, the output is empty -

It would be very helpful if you could add the sample input video for checking the code.

Hello everybody,

When I run main.py, I get the following error :

Traceback (most recent call last):
  File "/home/mounir/PycharmProjects/Human-detection-and-Tracking-master/main.py", line 137, in <module>
    recognizer.read("model.yaml")
cv2.error: OpenCV(4.0.0-pre) /home/mounir/opencv/modules/core/src/persistence_c.cpp:757: error: (-2:Unspecified error) The node is neither a map nor an empty collection in function 'cvGetFileNodeByName'

I have the latest OpenCV version installed

Details

• Exact error or Issue details
• **OpenCV Version ** : 4.0.0-pre (I know you told us to opt for 3.1.1
• Python Version : 3.6
• Operating System : Ubuntu 18.04
• Changes done, if any in the original code : Yes, some changes have been done.

recognizer = cv2.face.LBPHFaceRecognizer_create()
instead of
recognizer = cv2.face.createLBPHFaceRecognizer()

and

recognizer.read("model.yaml")
instead of
recognizer.load("model.yaml")

Thanks for your help !

• Exact error or Issue details
  when i run the code with this command python3 main.py in terminal i got this following error :
  usage: main.py [-h] -v VIDEOS
  main.py: error: the following arguments are required: -v/--videos
  OpenCV Version = 3.2.0
  Python Version = 3.6.5
  Operating System = ubuntu 18.04

I am trying to recognize faces from a .mp4 file. I already have some sample images of faces in my database. When I run the program, I want it to recognize the faces from the video. The location of video file is passed as a command line argument sys.argv[1].

code :

import cv2
import numpy as np
import os
import sqlite3
import pickle
from PIL import Image
import sys


faceDetect = cv2.CascadeClassifier('haarcascade_frontalface_default.xml');



rec = cv2.createLBPHFaceRecognizer();

rec.load("recognizer\\trainningData.yml")
path ='dataSet'

font=cv2.cv.InitFont(cv2.cv.CV_FONT_HERSHEY_SIMPLEX,1,1,0,2,2)
font2=cv2.cv.InitFont(cv2.cv.CV_FONT_HERSHEY_SIMPLEX,1,1,0,1,1)
def getProfile(id):
    conn=sqlite3.connect("FaceBase.db")
    cmd="SELECT * FROM People WHERE ID="+str(id)
    cursor = conn.execute(cmd)
    profile=None
    for row in cursor:
        profile=row
    conn.close()
    return profile


cam = cv2.VideoCapture(sys.argv[1])


while cam.isOpened():

    ret,img = cam.read()

    gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

    faces = faceDetect.detectMultiScale(gray,1.3,5);
    for(x,y,w,h) in faces :
        cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),2)
        id,conf=rec.predict(gray[y:y+h,x:x+w])

        if conf<60   :
                        profile=getProfile(id)
            if(profile!=None):
                cv2.cv.PutText(cv2.cv.fromarray(img),str(profile[1]),(x,y+h+30),font,255);
                cv2.cv.PutText(cv2.cv.fromarray(img),str(profile[2]),(x,y+h+60),font,255);
                cv2.cv.PutText(cv2.cv.fromarray(img),str(profile[3]),(x,y+h+90),font,255);
                print("{} is Correctly Recognized with confidence {}".format(id,conf))

        else :
             cv2.cv.PutText(cv2.cv.fromarray(img),'unkown',(x,y+h+30),font,255);


    cv2.imshow("Face",img);
    if (cv2.waitKey(1) == ord('q')):
        break;
cam.release()
cv2.destroyAllWindows()

The command in command prompt is

C:\FaceRocogProject\Face Recog sqlite\python Recognize_video.py 'C:\FaceRocogProject\Face Recog sqlite\test.mp4'

Hello,

I have tried to follow your instructions from Issue#25, but could not manage to make it work. When I am trying to run the command py create_face_model.py -i data/ I am getting the following error:
ImportError: No module named cv2

Also, if I erase the first line on create_face_model.py, #!/usr/bin/python, I am getting this error:
C:\projects\opencv-python\opencv\modules\highgui\src\window.cpp:636: error: (-2) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Carbon support. If yo
u are on Ubuntu or Debian, install libgtk2.0-dev and pkg-config, then re-run cmake or configure script in function cvShowImage

Thank you in advance.
I am using python 3.6