In Traction

Fun with Python, OpenCV and face detection

I had some fun with Gary Bishop’s OpenCV Python wrapper this morning. I wanted to try out OpenCV for detecting faces using a web cam. This could be used for instance to see if someone is sitting behind his desk or not. I used Gary’s Python wrapper since I didn’t want to code in C++.

I didn’t know where to start, so I searched for existing OpenCV face detection examples. I found a blog post by Nirav Patel explaining how to use OpenCV’s official Python bindings to perform face detection. Nirav will be working on a webcam module for Pygame for the Google Summer of Code.

I managed to rewrite Nirav’s example to get it working with CVtypes:

Here’s the code. Although it’s just a quick and dirty hack, it might be useful to others. It requires CVtypes and OpenCV, and was tested on Ubuntu Hardy with a Logitech QuickCam Communicate Deluxe webcam. You will need Nirav’s Haar cascade file as well.

import sys
from CVtypes import cv
 
def detect(image):
    image_size = cv.GetSize(image)
 
    # create grayscale version
    grayscale = cv.CreateImage(image_size, 8, 1)
    cv.CvtColor(image, grayscale, cv.BGR2GRAY)
 
    # create storage
    storage = cv.CreateMemStorage(0)
    cv.ClearMemStorage(storage)
 
    # equalize histogram
    cv.EqualizeHist(grayscale, grayscale)
 
    # detect objects
    cascade = cv.LoadHaarClassifierCascade('haarcascade_frontalface_alt.xml', cv.Size(1,1))
    faces = cv.HaarDetectObjects(grayscale, cascade, storage, 1.2, 2, cv.HAAR_DO_CANNY_PRUNING, cv.Size(50, 50))
 
    if faces:
        print 'face detected!'
        for i in faces:
            cv.Rectangle(image, cv.Point( int(i.x), int(i.y)),
                         cv.Point(int(i.x + i.width), int(i.y + i.height)),
                         cv.RGB(0, 255, 0), 3, 8, 0)
 
if __name__ == "__main__":
    print "OpenCV version: %s (%d, %d, %d)" % (cv.VERSION,
                                               cv.MAJOR_VERSION,
                                               cv.MINOR_VERSION,
                                               cv.SUBMINOR_VERSION)
 
    print "Press ESC to exit ..."
 
    # create windows
    cv.NamedWindow('Camera', cv.WINDOW_AUTOSIZE)
 
    # create capture device
    device = 0 # assume we want first device
    capture = cv.CreateCameraCapture(0)
    cv.SetCaptureProperty(capture, cv.CAP_PROP_FRAME_WIDTH, 640)
    cv.SetCaptureProperty(capture, cv.CAP_PROP_FRAME_HEIGHT, 480)    
 
    # check if capture device is OK
    if not capture:
        print "Error opening capture device"
        sys.exit(1)
 
    while 1:
        # do forever
 
        # capture the current frame
        frame = cv.QueryFrame(capture)
        if frame is None:
            break
 
        # mirror
        cv.Flip(frame, None, 1)
 
        # face detection
        detect(frame)
 
        # display webcam image
        cv.ShowImage('Camera', frame)
 
        # handle events
        k = cv.WaitKey(10)
 
        if k == 0x1b: # ESC
            print 'ESC pressed. Exiting ...'
            break

A known problem is that pressing the escape key doesn’t quit the program. Might be something wrong in my use of the cv.WaitKey function. Meanwhile you can just use Ctrl+C. All in all, the face detection works pretty well. It doesn’t recognize multiple faces yet, but that might be due to the training data. It would be interesting to experiment with OpenCV’s support for eye tracking in the future.

Update: the script does recognize multiple faces in a frame. Yesterday when Alex stood at my desk, it recognized his face as well. I think it didn’t work before because I used cv.Size(100, 100) for the last parameter of cv.HaarDetectObjects instead of cv.Size(50, 50). This parameter indicates the minimum face size (in pixels). When people were standing around my desk, they were usually farther away from the camera. Their face was then probably smaller than 100×100 pixels.

Just a quick note on ctypes. I remember when I created PydgetRFID that I tried to use libphidgets’ SWIG-generated Python bindings, but couldn’t get them to work properly. I had read about ctypes, and decided to use it for creating my own wrapper around libphidgets. Within a few hours I had a working prototype. When you’re struggling with SWIG-generated Python bindings, or have some C library without bindings that you would like to use, give ctypes a try. Gary Bishop wrote about a couple of interesting ctypes tricks to make the process easier.

Tags: CVtypes, facade, facedetection, opencv, programming, python, webcam

This entry was posted on Friday, June 27th, 2008 at 3:08 pm and is filed under Uncategorized. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.

View Comments to “Fun with Python, OpenCV and face detection”

In Traction » Blog Archive » Small update on face detection post Says:
June 27th, 2008 at 9:03 pm
[...] Blog « Fun with Python, OpenCV and face detection [...]
Si Says:
June 28th, 2008 at 8:09 am
excellent stuff. Many thanks
Jo Vermeulen Says:
June 28th, 2008 at 10:53 am
You're welcome! I'm glad you find it useful.
Nirav Patel Says:
June 30th, 2008 at 9:57 pm
Just to clarify, the Haar cascade file is one of the sample ones that comes with OpenCV. The script I wrote was based on the OpenCV face detection sample too, but using gstreamer instead of OpenCV's HighGUI to interface the webcam (HighGUI didn't support the camera in the XO).

Its good that you got it working though. There is some pretty amazing stuff in OpenCV.
Jo Vermeulen Says:
July 1st, 2008 at 1:34 am
You are right, I noticed yesterday that the cascade file was part of OpenCV. Thanks for clarifying!
daxroc Says:
July 2nd, 2008 at 4:09 pm
Nice script , worked fine for me @30fps
Jhon Says:
September 25th, 2008 at 2:18 pm
I figured it out how to properly use cvWaitKey.

In your code you are waiting just 10 ms for a key, and only after the image was processed.
So, if you wait a little bit longer(maybe 100ms, but this will slow down a lot the fps) you will be able to catch the keys.

However, there is also another problem cvWaitKey returns -1 when no key was pressed, but return a string(char) holding the key pressed, so you need to do the following:
if k!=-1 and ord(k) == 0x1b: # ESC
print 'ESC pressed. Exiting …'
break
Jo Vermeulen Says:
October 12th, 2008 at 7:25 am
Ah thanks, that's very helpful!
randomm Says:
October 17th, 2008 at 9:26 am
this is great stuff! thanks for this…

We managed to get up to 4 faces recognized at the same time.
Jo Vermeulen Says:
October 17th, 2008 at 9:29 am
You're welcome, I'm glad it was useful for you.
Playing with VideoCapture on Windows « Coding AI Says:
December 10th, 2008 at 6:52 pm
[...] detection, I just found that OpenCV has camera capture program built in. Somebody has been playing (Fun with Python, OpenCV and face detection) with it for a while. His approach is to use a OpenCV python wrapper – CVtypes , the premise is to [...]
Venkat Says:
January 4th, 2009 at 3:32 pm
When I tried runing the above code in windows xp, encountered the following error.

D:SWCamFD>python test2.py
Traceback (most recent call last):
File “test2.py”, line 2, in <module>
from CVtypes import cv
File “D:SWCamFDCVtypes.py”, line 42, in <module>
_cxDLL = cdll.cxcore100
File “C:Python25libctypes__init__.py”, line 423, in getattr
dll = self._dlltype(name)
File “C:Python25libctypes__init__.py”, line 348, in init
self._handle = _dlopen(self._name, mode)
WindowsError: [Error 126] The specified module could not be found

Any help regarding this will be great!
Jo Vermeulen Says:
January 5th, 2009 at 4:38 am
You need to have OpenCV installed. I guess that is the problem. I didn't try it on Windows yet since there's no D-BUS support, but in theory the face detection code should work.

I will probably release a first version of the code in the following weeks, so stay tuned!
Simon Says:
January 8th, 2009 at 9:26 pm
Hello, Sir
I'm from Asia. I'm just starting to learn openCV.
Is there any opinion or advise from Sir as an expert to me to start learning opencv

Thank you very much.
Face Detection in Static Images with Python Says:
February 20th, 2009 at 11:31 pm
[...] it seems that most OpenCV face detector examples are meant to be run “live”, usually taking the image from a webcam and highlighting [...]
Ecommerce Web Design Says:
April 17th, 2009 at 1:25 am
WaitKey function. Meanwhile you can just use Ctrl+C. All in all, the face detection works pretty well. It doesnâ��t recognize multiple faces yet, but that might be due to the training data.
How Do You Look When Merging Fails ;-) « Andi Albrecht Says:
May 9th, 2009 at 8:16 am
[...] the way how to access the camera is inspired by this nice blog post about face recognition using [...]
affordabletermquote Says:
May 11th, 2009 at 2:56 am
I am into doing same stuff but sad to say I'm still at the first phase of learning. I look forward to being like you so I can also share my know how for others to use.
uuganbaatar Says:
May 19th, 2009 at 2:14 pm
how is running? fast or not? I think opencv is universal thing… if u write your own codes it will be faster than opencv because there too many functions and processes unneedful… so goodluck!!!
gabox Says:
May 30th, 2009 at 6:15 pm
hi i want to put the window's webcam in other program both under python, but i dont how to do it, the project is a program with bottons and they controll a robot and the robot get the webcam, by the way im using linux mint 6
nop Says:
August 9th, 2009 at 2:36 am
Hello!
Your if script silently hangs on this line for me:
cascade = cv.LoadHaarClassifierCascade('haarcascade_frontalface_alt.xml', cv.Size(1,1))

What can be the problem here? This xml exists in same directory and the is no any error output.

Thanks in advance!
Jo Vermeulen Says:
August 10th, 2009 at 7:22 am
Are you using Ubuntu?
Jo Vermeulen Says:
August 10th, 2009 at 7:23 am
It might be good to use a specific GUI toolkit in this case, such as WxWindows.

Have a look at Gary Bishop's blog post, where he grabs a bitmap from the camera and displays this in a Wx window: http://wwwx.cs.unc.edu/~gb/wp/blog/2007/02/04/p…;
ClubPenguinCheats Says:
August 20th, 2009 at 7:32 pm
The script I wrote was based on the OpenCV face detection sample too, but using gstreamer instead of OpenCV's HighGUI to interface the webcam (HighGUI didn't support the camera in the XO).
sreeraj Says:
August 27th, 2009 at 1:00 pm
hi, i'm having this problem when i'm running your code..

i have an integrated camera on my laptop, which works with some apps like cheese.

while running this code, the camera(led) turns on, but nothing comes on the screen.
the script hangs and i have to ctrl+C to close it.

any pointers to help me with this situation will be appreciated.
thanks
cyril Says:
September 11th, 2009 at 12:00 pm
Hello, i try your code but i have this:

cyril@zilo2:~/Bureau/test$ sudo python webcam2.py
Traceback (most recent call last):
File “webcam2.py”, line 3, in <module>
from CVtypes import cv
ImportError: No module named CVtypes

i use ubuntu, how cab i install opencv? sudo apt-get install ?

Thinks @+
nop Says:
September 13th, 2009 at 7:26 am
yes, 9.04
nop Says:
September 13th, 2009 at 7:39 am
In synaptic you can fing python-opencv
cyril84 Says:
September 14th, 2009 at 3:08 pm
Hello, i have this:

Traceback (most recent call last):
File “opencv.py”, line 2, in <module>
from CVtypes import cv
ImportError: No module named CVtypes

What is this mistake? how install cvtypes?

Thinks
cyril84 Says:
September 14th, 2009 at 3:10 pm
I have do sudo apt-get install python-opencv. It is already installed. What can i do?
online games Says:
September 23rd, 2009 at 5:23 pm
I'm still having trouble with the escape key. Any tips?
Jo Vermeulen Says:
October 30th, 2009 at 6:39 am
The script uses Gary Bishop's CVtypes, not python-opencv.
In Traction » Blog Archive » Facade update: code available and information about related student projects Says:
October 30th, 2009 at 3:59 pm
[...] previous posts on face detection with Python and on changing the user’s presence when he/she is detected by the webcam are two of the most [...]
club penguin cheats Says:
November 4th, 2009 at 9:25 am
this is awesome, i have been wanting to do this with python for awhile now. great stuff.
njay Says:
November 13th, 2009 at 12:35 am
hey!! i am nj here, i am trying to execute this program on windows I am getting following error. I saw a post with same thing, where u said u will be releasing new version so that it works on windows. Is it not released yet?
Jo Vermeulen Says:
November 13th, 2009 at 7:06 am
You should install OpenCV first, and try to run the simple_winclient.py script. The software is available at my website.
the-maxx Says:
December 4th, 2009 at 2:50 pm
hi, i stumbled upon your little nice python script a few days ago and ported it to opencv 2.0 with its new python bindings. Hope anyone is interested, maybe you can update your version with this.

import sys
import cv

class FaceDetect():
def init(self):
cv.NamedWindow (“CamShiftDemo”, 1)
device = 0
self.capture = cv.CaptureFromCAM
capture_size = (320,200)
cv.SetCaptureProperty(self.capture, cv.CV_CAP_PROP_FRAME_WIDTH, capture_size⁰)
cv.SetCaptureProperty(self.capture, cv.CV_CAP_PROP_FRAME_HEIGHT, capture_size¹)

def detect(self):
cv.CvtColor(self.frame, self.grayscale, cv.CV_RGB2GRAY)

#equalize histogram
cv.EqualizeHist(self.grayscale, self.grayscale)

# detect objects
faces = cv.HaarDetectObjects(image=self.grayscale, cascade=self.cascade, storage=self.storage, scale_factor=1.2,
min_neighbors=2, flags=cv.CV_HAAR_DO_CANNY_PRUNING)

if faces:
#print 'face detected!'
for i in faces:
if i¹ > 10:
cv.Circle(self.frame, ((2*i⁰[0]+i⁰[2])/2,(2*i⁰[1]+i⁰[3])/2), (i⁰[2]+i⁰[3])/4, (128, 255, 128), 2, 8, 0)

def run(self):
# check if capture device is OK
if not self.capture:
print “Error opening capture device”
sys.exit(1)

self.frame = cv.QueryFrame(self.capture)
self.image_size = cv.GetSize(self.frame)

# create grayscale version
self.grayscale = cv.CreateImage(self.image_size, 8, 1)

# create storage
self.storage = cv.CreateMemStorage(128)
self.cascade = cv.Load('haarcascade_frontalface_default.xml')

while 1:
# do forever
# capture the current frame
self.frame = cv.QueryFrame(self.capture)
if self.frame is None:
break

# mirror
cv.Flip(self.frame, None, 1)

# face detection
self.detect()

# display webcam image
cv.ShowImage('CamShiftDemo', self.frame)
# handle events
k = cv.WaitKey(10)

if k 0x1b: # ESC
print 'ESC pressed. Exiting …'
break
sys.exit(1)

if __name__ “main“:
print “Press ESC to exit …”
face_detect = FaceDetect()
face_detect.run()
the-maxx Says:
December 4th, 2009 at 2:52 pm
argh, it killed my tabs!!!
Jo Vermeulen Says:
December 7th, 2009 at 3:21 pm
Thanks a lot! I'll give it a try!
Forrest Says:
December 17th, 2009 at 11:53 pm
So cool. Python can make opencv more easy and funny.
gisnap Says:
December 23rd, 2009 at 3:20 am
Its really cool, I came to know this really worth visiting, just bookmarked your site.

http://gisnap.com/
The place where fun never ends
selva Says:
December 30th, 2009 at 3:44 am
hi…hw can i edit this coding so that i can detect an image that i have saved. i'm using ubuntu 9.04….need ur help…thank u…
samsnaap Says:
December 30th, 2009 at 8:42 am
its been great coming across your site.however is there a way for me detect and display the available webcams conected to a pc.i tried searching online buy couldnt comeup with anything.Pygame 1.9 however has a module to take care of that.but the problem with pygame is .i cant include it in the gui of my project.not can i attach any stuff like buttons onto the defaul gui provided.would really appreciate if you could help my out.thanks in advance
Jo Vermeulen Says:
January 4th, 2010 at 3:41 am
I know there is a function to get the number of cameras:

cvcamGetCamerascount()

Maybe that helps?
samsnaap Says:
January 5th, 2010 at 10:39 am
thanks jo.well i kindda figured a way out last week. and these are basically the codes
def listWebcam(self,path='/dev'):
“”"detects the available webcam mounted to a computer “”"
devicelist = []
for device in os.listdir(path):#loops through devices all mounted devices
if device.startswith('video'):#returns true if a device with video prefix is found
devicenum = device.rsplit('o')#seperates video from the device index
devicelist.append(devicenum¹)
return devicelist
Jo Vermeulen Says:
January 5th, 2010 at 10:53 am
That's Linux-specific of course, but will indeed do the trick.
samsnaap Says:
January 5th, 2010 at 11:09 am
yup,sorry i guess i forgot to mention i was looking for linux specific solution.
oh and by the way.i do have some issues with the camera though.when i connect to the webcam.sometimes it just doesnt connect and the entire application just closes.
that is when i change the device value to different numbers .”self.capture = cv.CaptureFromCAM.i tested it with three webcams connected.it connected to two but not to the third.and then i removed the third and it just connected to one.
any idea why this is happening
Failface – So you can relive that magic moment again and again « Wat Vervelend! Says:
January 12th, 2010 at 1:05 am
[...] site. Strange! Well, I still managed to put together a small prorgram (borrowing heavily from here) called grabface that grabs a picture using the webcam and then figures out the position of your [...]
AlexMikhalev Says:
January 12th, 2010 at 8:13 am
Thank you for posting it online. I find it useful.
Jo Vermeulen Says:
January 12th, 2010 at 8:26 am
You're welcome! I'm glad you found it useful.
Free Games Says:
January 19th, 2010 at 3:24 am
Really-really helpful! Thank you so much for sharing this code
auttapong Says:
January 20th, 2010 at 3:59 am
hi. i have this
Null pointer (Invalid classifier cascade)
in function cvHaarDetectObjects,
C:UserVPoperncvcvsrccvhaar.cpp(890)
Jo Vermeulen Says:
January 20th, 2010 at 4:48 am
Are you sure you have the cascade file in the same directory?
auttapong Says:
January 20th, 2010 at 4:58 am
C:DevOpenCVdatahaarcascades
Jo Vermeulen Says:
January 20th, 2010 at 5:11 am
I currently don't have a Linux machine for testing, but IIRC the line

cascade = cv.LoadHaarClassifierCascade('haarcascade_frontalface_alt.xml', cv.Size(1,1))

requires the cascade file to be in the same directory as the script.

By the way, the script I presented in this blog post won't work on Windows. You should use the simple_winclient.py script for that (which can be found in the tarball available from my website).
auttapong Says:
January 20th, 2010 at 8:31 am
thank you very much Jo ^^
Jo Vermeulen Says:
January 20th, 2010 at 8:33 am
You're welcome!
auttapong Says:
January 20th, 2010 at 9:59 am
hi. i have this
Null pointer (Invalid classifier cascade)
in function cvHaarDetectObjects,
C:UserVPoperncvcvsrccvhaar.cpp(890)
Jo Vermeulen Says:
January 20th, 2010 at 10:48 am
Are you sure you have the cascade file in the same directory?
auttapong Says:
January 20th, 2010 at 10:58 am
C:DevOpenCVdatahaarcascades
Jo Vermeulen Says:
January 20th, 2010 at 11:11 am
I currently don't have a Linux machine for testing, but IIRC the line

cascade = cv.LoadHaarClassifierCascade('haarcascade_frontalface_alt.xml', cv.Size(1,1))

requires the cascade file to be in the same directory as the script.

By the way, the script I presented in this blog post won't work on Windows. You should use the simple_winclient.py script for that (which can be found in the tarball available from my website).
auttapong Says:
January 20th, 2010 at 2:31 pm
thank you very much Jo ^^
Jo Vermeulen Says:
January 20th, 2010 at 2:33 pm
You're welcome!
TechB Says:
March 2nd, 2010 at 8:00 am
Hey great post. I can't wait to get started hacking it to my needs. I made a script that tracts an IR LED and maps the mouse to the movements(http://hackaday.com/2010/02/25/python-ir-tracking-for-the-handicapped/).

I used VideoCapture(http://videocapture.sourceforge.net/) for the webcam interface though. I'm going to try and map the mouse movements to this new face-recognition.
TechB Says:
March 11th, 2010 at 5:28 pm
After about a week of work, I couldn't get opencv to work. I used VideoCapture again, and fdlib.dll to detect the faces. http://www.kyb.mpg.de/bs/people/kienzle/facedem…;
1john01 Says:
April 6th, 2010 at 8:05 am
Me and my friend want to set up a funny type call of duty video type thing, but to do so we would need to. BlackStar69
1john01 Says:
April 6th, 2010 at 8:05 am
Me and my friend want to set up a funny type call of duty video type thing, but to do so we would need to. BlackStar69
Stefan Says:
April 12th, 2010 at 11:09 pm
Hey,

I just found your amazing code on the web. I'm trying to make a eye tracking device for a paralized girl. I tryed your code but got this error.
Can you help me with this problem. I really don't know what to do.

Traceback (most recent call last):
File “D:My DocumentsMijn documentenTWGanotherdetection.py”, line 65, in <module>
detect(frame)
File “D:My DocumentsMijn documentenTWGanotherdetection.py”, line 22, in detect
faces = cv.HaarDetectObjects(grayscale, cascade, storage, 1.2, 2, cv.HAAR_DO_CANNY_PRUNING, cv.Size(50, 50))
WindowsError: exception: access violation reading 0×00000028

Thx,

Stefan (from the Netherlands)
Stefan Says:
April 13th, 2010 at 8:03 am
Hey,
I found the solution already. Needed to put the
'haarcascade_frontalface_default.xml' file in the same directory as your little programm. When I runned the code, it seems to work fine. I only noticed that the program is often detecting my chin and mouth.. and not the whole face. Is this because I'm to close to my cam or is there a other solution for.

Thx,

Stefan

ps: I also needed to put “from opencv.highgui import *” above the code. Did yours work without?
Payday Loans Says:
April 20th, 2010 at 12:34 am
OpenCV has reasonably robust Python interface created with SWIG. This makes it easy to integrate with existing libraries like Pygame and olpcgames. As an example, OpenCV can be combined with Pygame to make a simple face tracking xeyes clone.
Thanks.
Phifo Says:
May 4th, 2010 at 3:05 am
dont work for me

from CVtypes import cv
ImportError: No module named CVtypes
public records Says:
May 11th, 2010 at 9:58 am
i read this and detection is one component of … It is a simple python script that will connect to your webcam
stuaxo Says:
June 15th, 2010 at 11:15 pm
“When youâ��re struggling with SWIG-generated Python bindings, or have some C library without bindings that you would like to use, give ctypes a try. “

This reminded me of this
“If you have a problem – if no one else can help – and if you can find
them – maybe you can hire: The A-Team.”

I almost want somebody to geekerise the lyrics and make them about ctypes now.
links for 2010-06-19 | andy.edmonds.be Says:
June 20th, 2010 at 2:04 am
[...] In Traction Â» Blog Archive Â» Fun with Python, OpenCV and face detection (tags: python opencv webcam facedetection face) Published: June 20, 2010 Filed Under: Delicious Leave a Comment Name: Required [...]
The Magic Jack Says:
July 2nd, 2010 at 11:27 pm
wow thats some crazy code
air climber Says:
July 3rd, 2010 at 11:58 pm
I got lost half way through your code
air jordan 13 Says:
July 5th, 2010 at 6:19 am
Mark S. is definitely on the right track. If you want to get a professional looking email address, Id recommend buying your name domain name, like or
Gucci sweaters
If its common it might be difficult to get, however, be creative and you can usually find something.
800 calorie diet Says:
July 13th, 2010 at 2:34 am
Golden. Great, useful info.
rickdouglas85 Says:
August 2nd, 2010 at 1:00 am
Absolutely incredible – technology is certainly an amazing thing!

—
Rick, MJ Researcher
Matt Says:
August 2nd, 2010 at 5:35 am
Nice! I've got some motion detection going on over here if you're interested: http://appdelegateinc.com/blog/2010/08/02/motio…;

Did you buy the book? I find the OpenCV documentation is very hard to follow.
amitjhsaps123 Says:
August 22nd, 2010 at 10:09 am
Muito obrigado pelos elogios…de coraÃ§Ã£o.
Se depender de mim, estarei sempre compartlhando minha paixÃ£o, que sÃ£o os games!!
Quanto a fase da aranha realmente eh dificil, mas Ã© ali onde vc realmente fica “ninja” nas suas habilidades , e ai o resto do game fica muito mais atenuado, hehe como se fosse uma academia essa fase, rs.
AbraÃ§Ã£o amigo
online jogos

Fun with Python, OpenCV and face detection

View Comments to “Fun with Python, OpenCV and face detection”

Leave a Reply