Related
Hey, I want to share a global NumpyArray(cameraImg) between my main
programm and the process which runs parallel. But it doesn't work. It says
"TypeError: only size-1 arrays can be converted to Python scalars"
The main Programm displa_camera() runs in a While Loop, and gets the Image of the Webcam. The img is saved in global cameraImg and used in recognize_faces() to identifiy the face depcit in the Image. It saves the name, which is added to the Image, above the Persons head. Hope you can help me, thx
import time, os, cv2 as cv2, face_recognition
from multiprocessing import Process, Array, Value
global name
name=""
window_name = 'facerecognition'
def display_camera():
cap = cv2.VideoCapture(0)
cap.set(3, 640) # set Width
cap.set(4, 480) # set Height
cascade = cv2.CascadeClassifier('cascade.xml')
global cameraImg, name
while True:
ret, img = cap.read()
cameraImg=Array('d',img)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = cascade.detectMultiScale(
gray,
scaleFactor=1.2,
minNeighbors=5,
minSize=(20, 20)
)
for (x, y, w, h) in faces:
cv2.rectangle(img, (x, y), (x + w, y + h), (36, 255, 12), 1)
cv2.putText(img, name, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (36, 255, 12), 2)
roi_gray = gray[y:y + h, x:x + w]
roi_color = img[y:y + h, x:x + w]
cv2.imshow('video', img)
k = cv2.waitKey(30) & 0xff
if k == 27: # press 'ESC' to quit
break
cap.release()
cv2.destroyAllWindows()
def recognize_Faces():
global cameraImg, name
folder_dir = "../images/"
image_List=[]
for images in os.listdir(folder_dir):
# check if the image ends with png or jpg or jpeg
if (images.endswith(".png") or images.endswith(".jpg") \
or images.endswith(".jpeg")):
# display
image_List.append(images)
while True:
try:
newFaces=False
for path in image_List :
rgb_img = cv2.cvtColor(cameraImg, cv2.COLOR_BGR2RGB)
img_encoding = face_recognition.face_encodings(rgb_img)
img2 = cv2.imread("../images/"+path)
rgb_img2 = cv2.cvtColor(img2, cv2.COLOR_BGR2RGB)
img_encoding2 = face_recognition.face_encodings(rgb_img2)[0]
result = face_recognition.compare_faces(img_encoding, img_encoding2)
print("Result: ", result)
if(result[0]):
newFaces=True
name= os.path.basename("../images/"+path).split('.')[0]
except Exception as e:
print(e)
if(newFaces==False):
name=""
k = cv2.waitKey(30) & 0xff
if k == 27: # press 'ESC' to quit
break
time.sleep(3)
if __name__ == '__main__':
secondaryThread = Process(target=recognize_Faces)
secondaryThread.start()
display_camera()
I am developing a facial recognition system and for that I have selected LBPH algorithm for doing the task. I have collected the sample images of user and trained it. The problem is while recognizing the face, the predict() of LBPHRecognizer always return same value for label but different value for confidence. Even if the face is unknown it returns 1.
Technologies I have been using : Python 3.7.4, OpenCV 4.1.2
Code to collect sample image
import cv2
import numpy as np
import os
import requests
import time
from PIL import Image
class CollectFaceWebCam():
def __init__(self, sid):
self.studentId = sid
#capture webcam
self.LiveWebCamera = cv2.VideoCapture(0)
#pre-trained dataset (haar-cascade classifier)
self.faceDataSet = cv2.CascadeClassifier('resources/haarcascade_frontalface_default.xml')
#sample image capture counter
self.imgCounter = 0
self.directoryName = 'sampleImgFolder'
#check path
if not os.path.exists(self.directoryName):
os.makedirs(self.directoryName)
if not os.path.exists(self.directoryName + '/' + self.studentId):
os.makedirs(self.directoryName + '/' + self.studentId)
def gen(self):
while True:
condition, frame = self.LiveWebCamera.read() #capture frame
img = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)#conversion to gray scale
#face detection
faces = self.faceDataSet.detectMultiScale( # Detect face sizes
img,
scaleFactor=1.3,
minNeighbors=5,
minSize=(100, 100),
flags=cv2.CASCADE_SCALE_IMAGE
)
for (x, y, w, h) in faces:
end_crd_x = x + w # face start coordinates
end_crd_y = y + h #face end coordinate
#draw rectangle
##parms image, start plot, end plot, thickness, color
cv2.rectangle(frame, (x, y), (end_crd_x, end_crd_y), (0, 255, 33), 1)
#accepts multiple face
if len(faces) >= 0:
#face must be single in frame
if len(faces) == 1:
detectedImg = img[y:y + h, x:x + w]
#checking blurness of image
blurValue = cv2.Laplacian(detectedImg, cv2.CV_64F).var()
#ignoring the blury images
if not blurValue <= 60:
newImg = img[y:y + h, x:x + w] #new img
#saving the detected faces
filename = '{}\{}\{}\{}_{}'.format(os.getcwd(), self.directoryName, self.studentId, self.studentId, self.imgCounter) + '.jpg'
cv2.imwrite(filename, newImg)
self.imgCounter += 1
else:
cv2.putText(frame,"Multiple Face not allowed", (50,150), cv2.FONT_HERSHEY_SIMPLEX, 1, (237, 20, 5), thickness=2)
cv2.putText(frame,"Collecting Sample", (50,100), cv2.FONT_HERSHEY_SIMPLEX, 1, (250, 250, 250), thickness=3)
cv2.putText(frame,"Image Count " + str(self.imgCounter), (50,200), cv2.FONT_HERSHEY_SIMPLEX, 2, (237, 20, 5), thickness=2)
cv2.imshow('Collecting Sample', frame) # display frames
k = cv2.waitKey(100) & 0xff # capture when user press 'esc'
if k == 27:
break
elif self.imgCounter == 110:
break
self.LiveWebCamera.release() #stop video capture
cv2.destroyAllWindows() #close all windows
class CleanSampleImages():
def __init__(self):
self.faceDataset = cv2.CascadeClassifier('resources/haarcascade_frontalface_default.xml')
self.eyeDataset = cv2.CascadeClassifier('resources/haarcascade_eye.xml')
self.targetFolder = 'sampleImgFolder'
def checkFace(self):
os.chdir(self.targetFolder)
for directory in os.listdir():
os.chdir(directory)
for files in os.listdir():
imagePath = '{}/{}'.format(os.getcwd(), files)
imagePil = Image.open(imagePath).convert('L')
imageNumpy = np.array(imagePil) #conversion of normal image to numpy array
#detect face
faces = self.faceDataset.detectMultiScale(imageNumpy)
#deleting image file if face is not found
if not len(faces) == 1:
os.remove(files)
break
for (x, y, w, h) in faces:
#detect eye from selected
eyes = self.eyeDataset.detectMultiScale(imageNumpy)
if not len(eyes) > 0 and len(eyes) <=2:
#deleting image file if eye count of image is less than 0 or more than 2
os.remove(files)
os.chdir('../')
os.chdir('../')
#id must be in X-X-ID eg. a-b-342
t = CollectFaceWebCam('sa-t-1')
t.gen()
clean = CleanSampleImages
c.checkFace()
Above code consist of two class CollectFaceWebCam and CleanSampleImages. CollectFaceWebCam works for collecting the sample images. and CleanSampleImages works for cleaning the collected data. if the image does not consist of face the file is deleted.
Code to Train images
import os
import cv2
import numpy as np
from PIL import Image
class Trainer():
def __init__(self):
self.recognizer = cv2.face.LBPHFaceRecognizer_create()
self.targetImagesDirectory="sampleImgFolder"
self.dataset = cv2.CascadeClassifier('resources/haarcascade_frontalface_default.xml')
def getImgwithId(self):
sampleImage, sampleImageId = [], []
filename = '{}\\{}'.format(os.getcwd(), self.targetImagesDirectory)
if os.path.exists(filename):
os.chdir(filename)
print('current path is ' + os.getcwd())
for f in os.listdir():
imgPath = os.path.join(filename, f)
os.chdir(imgPath)
for file in os.listdir():
#reteving id from filename (filename format : ta-s-ID_Filename.jpg)
id = file.split('_')
id = id[0].split('-')
id = id[2]
imageFilePath = imgPath + '\\' + file
imagePil = Image.open(imageFilePath).convert('L')
#conversion to numpy array
imageNp = np.array(imagePil, 'uint8')
faces = self.dataset.detectMultiScale(imageNp)
for (x, y, w, h) in faces:
sampleImage.append(imageNp)
sampleImageId.append(id)
os.chdir('../')
os.chdir('../')
return sampleImage, np.array(sampleImageId, dtype = int)
def train(self, data, label):
try:
self.recognizer.train(data, label)
self.msg = 'Training Successful'
print('writting')
self.recognizer.write('date.yml')
print('writing finished')
except:
self.msg = 'Core: Training Error'
print('except')
tr = Trainer()
sampleFaces, sampleFaceId = (tr.getImgwithId())
tr.train(sampleFaces, sampleFaceId)
Code to recognize face
import os
import cv2
import numpy as np
from PIL import Image
class Recognizer():
def __init__(self):
self.recognizer = cv2.face.LBPHFaceRecognizer_create()
self.recognizer.read('date.yml')
self.targetImagesDirectory="sampleImgFolder"
self.dataset = cv2.CascadeClassifier('resources/haarcascade_frontalface_default.xml')
self.captureVideo = cv2.VideoCapture(0)
self.font = cv2.FONT_HERSHEY_SIMPLEX = 2 # Font
self.predictedUser = []
def gen(self):
while True:
condition, frame = self.captureVideo.read() #capture frame
img = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)#conversion to gray scale
#face detection
faces = self.dataset.detectMultiScale( # Detect face sizes
img,
scaleFactor=1.3,
minNeighbors=5,
minSize=(100, 100),
flags=cv2.CASCADE_SCALE_IMAGE
)
for (x, y, w, h) in faces:
end_crd_x = x + w # face start coordinates
end_crd_y = y + h #face end coordinate
#draw rectangle
##parms image, start plot, end plot, thickness, color
cv2.rectangle(frame, (x, y), (end_crd_x, end_crd_y), (0, 255, 33), 1)
predictUser, confidence = self.recognizer.predict(img[y:y+h,x:x+w])
self.predictedUser.append(predictUser)
cv2.imshow('test', frame)
k = cv2.waitKey(100) & 0xff # capture when user press 'esc'
if k == 27:
break
self.captureVideo.release()
cv2.destroyAllWindows()
r = Recognizer()
r.gen()
print(r.predictedUser)
"predictUser, confidence = self.recognizer.predict(img[y:y+h,x:x+w])" line of code in Recognizer class always return same value for label. The output of code to recognize face is attached below:
I would love to know why and where the problem is, as My skills and research could not lead me to identification of problem.
It might because of the data-collection process. I see you using a cascade classifier multiple times, you could limit it. While checking for a face on webcam, you could use classifiers at the time and store only the extracted/cropped faces. Also during prediction, use confidence as a threshold to limit the false prediction.
I am trying to detect a face using OpenCV. I have a file recognizer.py as follows:
import cv2
faceDetect = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
cam = cv2.VideoCapture(0)
rec = cv2.face.createLBPHFaceRecognizer()
rec.load('recognizer/trainningData.yml')
id = 0
font = cv2.FONT_HERSHEY_SIMPLEX
while True:
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, 0, 255), 2)
id, conf = rec.predict(gray[y:y + h, x:x + w])
cv2.putText(img, str(id), (x, y + h), font, 255, (255, 0, 0))
cv2.imshow("Face", img)
if cv2.waitKey(1) == ord('q'):
break
cam.release()
cv2.destroyAllWindows()
When I am trying to run this code, the program is running successfully and opening a camera window.
But whenever, I am trying to show my face in front of the camera, the program is terminating with exit code 1 and showing the following error:
Traceback (most recent call last):
File "/home/prateek/recognizer.py", line 15, in <module>
id, conf = rec.predict(gray[y:y + h, x:x + w])
TypeError: 'int' object is not iterable
Process finished with exit code 1
Means, I am getting the error on line 15 which is as follows:
id, conf = rec.predict(gray[y:y + h, x:x + w])
I don't know how to resolve this problem. I am using Python3 and OpenCV3.3.
Finally, I have got the solution. The problem with was version of opencv. This code is for opencv2.4 and I was trying to run it on opencv3.
Well, The final code for opencv3 is as following:
import cv2
faceDetect = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
cam = cv2.VideoCapture(0)
rec = cv2.face.createLBPHFaceRecognizer()
rec.load('recognizer/trainningData.yml')
id = 0
font = cv2.FONT_HERSHEY_SIMPLEX
while True:
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, 0, 255), 2)
id= rec.predict(gray[y:y + h, x:x + w])
cv2.putText(img, str(id), (x, y + h), font, 255, (255, 0, 0))
cv2.imshow("Face", img)
if cv2.waitKey(1) == ord('q'):
break
cam.release()
cv2.destroyAllWindows()
There is no need to mention the variable conf.
rec.predict(gray[y:y + h, x:x + w]) is returning the id of the person from the database.
I'm trying to create a aplication with opencv that overlaps a glass on me face. However, when the video appears the glasses have a black on the alpha layer. Here is my code:
video_capture = cv2.VideoCapture(0)
anterior = 0
glasses = cv2.imread('Glasses_1.png')
def put_glasses(glasses,fc,x,y,w,h):
face_width = w
face_height = h
glasses_width = int(face_width)
glasses_height = int(face_height*0.32857)
glasses = cv2.resize(glasses,(glasses_width,glasses_height))
for i in range(glasses_height):
for j in range(glasses_width):
for k in range(3):
if glasses[i][j][k]<235:
fc[y+i-int(-0.25*face_height)-1][x+j][k] = glasses[i][j][k]
return fc
while True:
if not video_capture.isOpened():
print('Unable to load camera.')
sleep(5)
pass
ret, frame = video_capture.read()
if ret is True:
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
else:
continue
faces = faceCascade.detectMultiScale(
gray,
scaleFactor=1.1,
minNeighbors=5,
minSize=(40,40)
)
for (x, y, w, h) in faces:
cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 255, 0), 2)
cv2.putText(frame,"Person Detected",(x,y),cv2.FONT_HERSHEY_SIMPLEX,1,(0,0,255),2)
frame = put_glasses(glasses, frame, x, y, w, h)
I will be very grateful if anyone could help.
You read the png in bgr format, not the bgra or unchanged format. Then I don't think your glass image in the program is shape of (h,w,4). You should read with flag cv2.IMREAD_UNCHANGED.
glasses = cv2.imread("xxx.png", cv2.IMREAD_UNCHANGED)
Maybe this link will help. How do I clear a white background in OpenCV with c++?
The bgra worm:
Blending:
My original python script was created to work on images already saved. I am now wanting it to capture the image and crop it. I have a working webcam section and a working crop section but I am not able to combine them and make them it. I have included the combined code. Currently it will still crop a saved image and the GUI for the webcam does display for a second but does not display any content (gray screen). Can anyone help me?
import cv
import cv2
import numpy
import Image
import glob
import os
# Static
faceCascade = cv.Load('haarcascade_frontalface_alt.xml')
padding = -1
inputimg = raw_input('Please enter the entire path to the image folder:')
outputimg = raw_input('Please enter the entire path to the output folder:')
if not os.path.exists(outputimg):
os.makedirs(outputimg)
while (padding < 0):
padding = int(raw_input('Enter crop padding:'))
capture = cv2.VideoCapture(0)
cv2.namedWindow("Face Crop")
if capture.isOpened():
frame = capture.read()
def DetectFace(image, faceCascade, returnImage=False):
#variables
min_size = (50,50)
haar_scale = 1.1
min_neighbors = 3
haar_flags = 0
DOWNSCALE = 4
# Equalize the histogram
cv.EqualizeHist(image, image)
# Detect the faces
faces = cv.HaarDetectObjects(image, faceCascade, cv.CreateMemStorage(0),haar_scale, min_neighbors, haar_flags, min_size)
# If faces are found
if faces and returnImage:
for ((x, y, w, h), n) in faces:
# Convert bounding box to two CvPoints
pt1 = (int(x), int(y))
pt2 = (int(x + w), int(y + h))
cv.Rectangle(image, pt1, pt2, cv.RGB(255, 0, 0), 5, 8, 0)
# Start video frame
minisize = (frame.shape[1]/DOWNSCALE,frame.shape[0]/DOWNSCALE)
miniframe = cv2.resize(frame, minisize)
faceCam = classifier.detectMultiScale(miniframe)
for f in faceCam:
x, y, w, h = [ v*DOWNSCALE for v in f ]
cv2.rectangle(frame, (x,y), (x+w,y+h), (0,0,255))
cv2.putText(frame, "Press ESC to close.", (5, 25),
cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255,255,255))
cv2.imshow("preview", frame)
# get next frame
frame = capture.read()
raw_input('Pause for testing')
key = cv2.waitKey(20)
if key in [27, ord('Q'), ord('q')]: # exit on ESC
break
if returnImage:
return image
else:
return faces
def pil2cvGrey(pil_im):
pil_im = pil_im.convert('L')
cv_im = cv.CreateImageHeader(pil_im.size, cv.IPL_DEPTH_8U, 1)
cv.SetData(cv_im, pil_im.tostring(), pil_im.size[0] )
return cv_im
def imgCrop(image, cropBox, boxScale=1):
# Crop a PIL image with the provided box [x(left), y(upper), w(width), h(height)]
# Calculate scale factors
xPadding=max(cropBox[2]*(boxScale-1),int(padding))
yPadding=max(cropBox[3]*(boxScale-1),int(padding))
# Convert cv box to PIL box [left, upper, right, lower]
PIL_box=[cropBox[0]-xPadding, cropBox[1]-yPadding, cropBox[0]+cropBox[2]+xPadding, cropBox[1]+cropBox[3]+yPadding]
return image.crop(PIL_box)
def Crop(imagePattern,boxScale=1):
imgList=glob.glob(imagePattern)
if len(imgList)<=0:
return
else:
for img in imgList:
pil_im=Image.open(img)
cv_im=pil2cvGrey(pil_im)
faces=DetectFace(cv_im,faceCascade)
if faces:
n=1
for face in faces:
croppedImage=imgCrop(pil_im, face[0],boxScale=boxScale)
fname,ext=os.path.splitext(img)
fname = os.path.basename(fname)
croppedImage.save(outputimg + '\\' + fname + ' -c' + ext)
n+=1
print 'Cropping:', fname
else:
print 'No faces found:', img
# Crop all images in a folder
Crop(inputimg + '\*.png', boxScale=1)
Crop(inputimg + '\*.jpg', boxScale=1)
Also, if anyone has any code improvements please let me know as I am new to Python.
I was able to fix this by reworking the logic and flow of code. Updated code below and on github, https://github.com/aDroidman/EyeonYou
import cv
import cv2
import numpy
import Image
import glob
import os
# Static
faceCascade = cv.Load('haarcascade_frontalface_alt.xml')
padding = -1
boxScale = 1
# Needed for webcam CV2 section
HaarXML = "haarcascade_frontalface_alt.xml"
classifier = cv2.CascadeClassifier(HaarXML)
downScale = 4
webcam = cv2.VideoCapture(0)
def DetectFace(image, faceCascade, returnImage=False):
#variables
min_size = (50,50)
haar_scale = 1.1
min_neighbors = 3
haar_flags = 0
DOWNSCALE = 4
# Equalize the histogram
cv.EqualizeHist(image, image)
# Detect the faces
faces = cv.HaarDetectObjects(image, faceCascade, cv.CreateMemStorage(0),haar_scale, min_neighbors, haar_flags, min_size)
# If faces are found
if faces and returnImage:
for ((x, y, w, h), n) in faces:
# Convert bounding box to two CvPoints
pt1 = (int(x), int(y))
pt2 = (int(x + w), int(y + h))
cv.Rectangle(image, pt1, pt2, cv.RGB(255, 0, 0), 5, 8, 0)
if returnImage:
return image
else:
return faces
def pil2cvGrey(pil_im):
pil_im = pil_im.convert('L')
cv_im = cv.CreateImageHeader(pil_im.size, cv.IPL_DEPTH_8U, 1)
cv.SetData(cv_im, pil_im.tostring(), pil_im.size[0] )
return cv_im
def imgCrop(image, cropBox, boxScale=1):
# Crop a PIL image with the provided box [x(left), y(upper), w(width), h(height)]
# Calculate scale factors
xPadding=max(cropBox[2]*(boxScale-1),int(padding))
yPadding=max(cropBox[3]*(boxScale-1),int(padding))
# Convert cv box to PIL box [left, upper, right, lower]
PIL_box=[cropBox[0]-xPadding, cropBox[1]-yPadding, cropBox[0]+cropBox[2]+xPadding, cropBox[1]+cropBox[3]+yPadding]
return image.crop(PIL_box)
def Crop(imagePattern,boxScale,outputimg):
imgList=glob.glob(imagePattern)
if len(imgList)<=0:
return
else:
for img in imgList:
pil_im=Image.open(img)
cv_im=pil2cvGrey(pil_im)
faces=DetectFace(cv_im,faceCascade)
if faces:
n=1
for face in faces:
croppedImage=imgCrop(pil_im, face[0],boxScale=boxScale)
fname,ext=os.path.splitext(img)
fname = os.path.basename(fname)
croppedImage.save(outputimg + '\\' + fname + ' -c' + ext)
n+=1
print 'Cropping:', fname
else:
print 'No faces found:', img
def CropSetup(padding, boxScale):
inputimg = raw_input('Please enter the entire path to the image folder:')
outputimg = raw_input('Please enter the entire path to the output folder:')
# Create output folder if missing
if not os.path.exists(outputimg):
os.makedirs(outputimg)
# Get padding for crop
while (padding < 0):
padding = int(raw_input('Enter crop padding:'))
# Crop images
Crop(inputimg + '\*.png', boxScale, outputimg)
Crop(inputimg + '\*.jpg', boxScale, outputimg)
print 'Option 1: Detect image from Webcam'
print 'Option 2: Crop saved images'
option = int(raw_input('Please enter 1 or 2: '))
def Webcam(webcam, classifier, downScale):
if webcam.isOpened():
rval, frame = webcam.read()
else:
rval = False
while rval:
# detect faces and draw bounding boxes
minisize = (frame.shape[1]/downScale,frame.shape[0]/downScale)
miniframe = cv2.resize(frame, minisize)
faces = classifier.detectMultiScale(miniframe)
for f in faces:
x, y, w, h = [ v*downScale for v in f ]
cv2.rectangle(frame, (x,y), (x+w,y+h), (0,0,255))
cv2.putText(frame, "Press ESC to close.", (5, 25),
cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255,255,255))
cv2.imshow("Face Crop", frame)
# get next frame
rval, frame = webcam.read()
key = cv2.waitKey(10)
if key in [27, ord('Q'), ord('q')]: # exit on ESC
break
if option == 1:
Webcam(webcam, classifier, downScale)
elif option == 2:
CropSetup(padding, boxScale)
else:
print 'Not a valid input'