I am trying to run some python 2.7 code with opencv2. Currently if a subject enters the frame the code labels them as the one it looks like most in its photo database. Instead of this I would like it to label untrained faces as "unknown" this is my code so far:
import cv2
import numpy as np
faceDetect=cv2.CascadeClassifier('haarcascade_frontalface_default.xml');
cam=cv2.VideoCapture(0);
rec=cv2.createLBPHFaceRecognizer();
rec.load("recognizer\\trainingData.yml")
id=0
font=cv2.cv.InitFont(cv2.cv.CV_FONT_HERSHEY_SIMPLEX,1,1,0,0)
#font=cv2.cv.InitFont(cv2.cv.CV_FONT_HERSHEY_COMPLEX_SMALL,3,1,0,1)
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),(0,255,255),2)
id,conf=rec.predict(gray[y:y+h, x:x+w])
if(id==1):
id="Admin"
cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,255),2)
elif(id==2):
id="Sonja"
cv2.rectangle(img,(x,y),(x+w,y+h),(255,255,255),2)
cv2.rectangle(img,(x,y),(x+w,y+h),(255,255,255),2)
cv2.cv.PutText(cv2.cv.fromarray(img),str(id),(x,y+h),font,(255,255,255));
cv2.imshow("Image",img);
if(cv2.waitKey(1)==ord('q')):
break;
cam.release()
cv2.destroyAllWindows()
And the trainer is run through this code:
import os
import cv2
import numpy as np
from PIL import Image
recognizer=cv2.createLBPHFaceRecognizer();
path='dataSet'
def getImagesWithID(path):
imagePaths=[os.path.join(path,f) for f in os.listdir(path)]
faces=[]
IDs=[]
for imagePath in imagePaths:
faceImg=Image.open(imagePath).convert('L');
faceNp=np.array(faceImg,'uint8')
ID=int(os.path.split(imagePath)[-1].split('.')[1])
faces.append(faceNp)
print ID
IDs.append(ID)
cv2.imshow("training",faceNp)
cv2.waitKey(10)
return np.array(IDs), faces
Ids, faces= getImagesWithID(path)
recognizer.train(faces, Ids)
recognizer.save('recognizer/trainingData.yml')
cv2.destroyAllWindows()
I assume that your rec.predict method returns the id of the recognized faces. In which case you can add an 'else' condition in the for (x,y,w,h) in faces: loop for the faces that don't have an id, like so:
if(id==1):
id="Admin"
cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,255),2)
cv2.putText(img,"Admin",x+h/2,y+w+40),cv2.FONT_HERSHEY_SIMPLEX,0.6,(0,255,255),2)
elif(id==2):
id="Sonja"
#cv2.rectangle(img,(x,y),(x+w,y+h),(255,255,255),2)
cv2.rectangle(img,(x,y),(x+w,y+h),(255,255,255),2)
cv2.putText(img,"Sonja",x+h/2,y+w+40),cv2.FONT_HERSHEY_SIMPLEX,0.6,(255,255,255),2)
else:
cv2.rectangle(img,(x,y),(x+w,y+h),(0,0,255),2)#Red
cv2.putText(img,"Unknown",(x+h/2,y+w+40),cv2.FONT_HERSHEY_SIMPLEX,0.6,(0,0,255),2)
Also, I've implemented the putText method differently than the one you've shown.
If you print the value of conf you can see that the value will be less than 70 if the face is in the dataset you made otherwise the value of conf will be more than 70. The value 70 is set by me if you want the system be more accurate check the value of conf and give any other value as your wish.
import cv2
import numpy as np
from time import sleep
faceDetect=cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
cam=cv2.VideoCapture(0)
rec=cv2.createLBPHFaceRecognizer()
rec.load("recognizer/trainingData.yml")
id=0
font=cv2.cv.InitFont(cv2.cv.CV_FONT_HERSHEY_COMPLEX_SMALL,1,1,0,1)
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), (255, 0, 0), 2)
id,conf=rec.predict(gray[y:y+h, x:x+w])
if(conf<70):
if(id==1):
id="Admin"
if(id==2):
id="Sonja"
else:
id="unknown"
cv2.cv.PutText(cv2.cv.fromarray(img), str(id), (x,y+h), font,255)
print ('ok')
cv2.imshow("Face",img)
if (cv2.waitKey(1) & 0xFF==ord('q')):
break
cam.release()
cv2.destroyAllWindows()
if conf<70:
if id !=0 & id !=1:
cv2.putText(img,"unknown",(x,y),cv2.FONT_HERSHEY_SIMPLEX,1,(0,255,0),2,cv2.LINE_AA)
Related
I am trying to run a facial recognition service on my Raspberry Pi, but it has suddenly stopped detecting faces
I am using python-opencv for this and the last time I tested it everything worked fine. The below code is for the the training the system on new faces
`
import cv2
import os
import numpy as np
from PIL import Image
import sqlite3
recognizer = cv2.createLBPHFaceRecognizer()
detector= cv2.CascadeClassifier("haarcascade_frontalface_default.xml");
cam = cv2.VideoCapture(0)
con = sqlite3.connect('Users.db')
cur = con.cursor()
Id=raw_input('Enter your id: ')
name=raw_input('Enter your name: ')
sampleNum=0
while True:
ret, img = cam.read()
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = detector.detectMultiScale(gray, 1.3, 5)
for (x,y,w,h) in faces:
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
#incrementing sample number
sampleNum=sampleNum+1
#saving the captured face in the dataset folder
cv2.imwrite("dataSet/User."+Id +'.'+ str(sampleNum) + ".jpg", gray[y:y+h,x:x+w])
cv2.imshow('frame',img)
#wait for 100 miliseconds
if cv2.waitKey(100) & 0xFF == ord('q'):
break
# break if the sample number is more than 20
elif sampleNum>30:
break
cam.release()
cv2.destroyAllWindows()
def getImagesAndLabels(path):
#get the path of all the files in the folder
imagePaths=[os.path.join(path,f) for f in os.listdir(path)]
#create empth face list
faceSamples=[]
#create empty ID list
Ids=[]
#now looping through all the image paths and loading the Ids and the images
for imagePath in imagePaths:
#loading the image and converting it to gray scale
pilImage=Image.open(imagePath).convert('L')
#Now we are converting the PIL image into numpy array
imageNp=np.array(pilImage,'uint8')
#getting the Id from the image
Id=int(os.path.split(imagePath)[-1].split(".")[1])
# extract the face from the training image sample
faces=detector.detectMultiScale(imageNp)
#If a face is there then append that in the list as well as Id of it
for (x,y,w,h) in faces:
faceSamples.append(imageNp[y:y+h,x:x+w])
Ids.append(Id)
return faceSamples,Ids
os.system("sudo rm trainer/trainer.yml")
faces,Ids = getImagesAndLabels('dataSet')
recognizer.train(faces, np.array(Ids))
recognizer.save('trainer/trainer.yml')
`
Normally it would open a window and show 30 photos in succession of the user's face, but now nothing shows up after it asks for a name. I have run other OpenCV applications and it can find faces in static images.
I had to replace the haar_cascade_frontalface.xml file
I have a problem in my code to detect someone's face in python2.7 and opencv3.3
import cv2
import numpy as np
faceDetect=cv2.CascadeClassifier("haarcascade_frontalface_default.xml")
cam=cv2.VideoCapture(0)
rec=cv2.face.LBPHFaceRecognizer_create()
rec.load("recognizer/trainningData.yml")
id=0
font=cv2.cv.InitFont(cv2.cv.CV_FONT_HERSHEY_COMPLEX_SMALL,5,1,0,4)
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.rextangle(img,(x,y),(x+w,y+h),(0,0,255),2)
id,conf=rec.predict(gray[y:y+h,x:x+w])
if id is 1:
id="Zakir Naik"
elif id is 2:
id="Erdogan"
elif id is 3:
id="Fachrul"
cv2.cv.PutText(cv2.cv.fromarray(img),str(id),(x,y+h),font,255)
cv2/imshow("Face",img)
if(cv2.waitKey(1)==ord("q")):
break;
cam.release()
cv2.destroyAllWindows()
Output
'cv2.face_LBPHFaceRecognizer' object has no attribute 'load'
OpenCV2 has a load function
OpenCV3 does not
Maybe try rec.read("recognizer/trainningData.yml")
I'm tying to use Keras for image recognition, but kept getting errors like:
ValueError: Error when checking input: expected input_9 to have 4 dimensions, but got array with shape (100, 300, 300)
I tried to change values for params that relate to dimensions, also tried to reshape images, but still got errors.
In fact, I don't understand why did I get this error. Why it expects 4 dimensions?
Here's my code:
import os
import numpy as np
import pandas as pd
import scipy
import sklearn
import keras
from keras.models import Sequential
from keras.layers import Dense, Activation, Dropout, Convolution2D, Flatten, MaxPooling2D, Reshape, InputLayer
import cv2
from skimage import io
import urllib2
from PIL import Image
import numpy as np
%matplotlib inline
I chose 50 rose images and 50 sunflower images from imagenet:
rose_file = "http://www.image-net.org/api/text/imagenet.synset.geturls?wnid=n04971313"
sunflower_file = "http://www.image-net.org/api/text/imagenet.synset.geturls?wnid=n11978713"
images = []
image_num = 50
rose_urls = urllib2.urlopen(rose_file)
rose_ct = 0
for rose_url in rose_urls:
try:
resp = urllib2.urlopen(rose_url)
rose_image = np.asarray(bytearray(resp.read()), dtype="uint8")
images.append(rose_image)
rose_ct += 1
if rose_ct == image_num: # only use 50 images here, otherwise, loading time is too long
break
except: # some images are no longer available
pass
sunflower_urls = urllib2.urlopen(sunflower_file)
sunflower_ct = 0
for sunflower_url in sunflower_urls:
try:
resp = urllib2.urlopen(sunflower_url)
sunflower_image = np.asarray(bytearray(resp.read()), dtype="uint8")
images.append(sunflower_image)
sunflower_ct += 1
if sunflower_ct == image_num: # only use 50 images here, otherwise, loading time is too long
break
except: # some images are no longer available
pass
Resize training images to 300*300:
from keras.utils.np_utils import to_categorical
for i in range(len(images)):
images[i]=cv2.resize(np.array(images[i]),(300,300))
images = np.array(images)
labels = [0 for i in range(image_num)]
labels.extend([1 for j in range(image_num)])
labels = np.array(labels)
labels = to_categorical(labels)
Build the model:
filters=10
filtersize=(5,5)
epochs=7
batchsize=128
input_shape=(300,300, 3)
model = Sequential()
model.add(keras.layers.InputLayer(input_shape=input_shape))
model.add(keras.layers.convolutional.Conv2D(filters, filtersize, strides=(1, 1),
padding='valid', data_format="channels_last", activation='relu'))
model.add(keras.layers.MaxPooling2D(pool_size=(2, 2)))
model.add(keras.layers.Flatten())
model.add(keras.layers.Dense(units=2, input_dim=10, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(images, labels, epochs=epochs, batch_size=batchsize, validation_split=0.3)
model.summary()
Here, I tried to change input_shape=(300,300, 3) into input_shape=(300,300, 3, 0), hoping this means 4 dimensions, but got errors saying:
Input 0 is incompatible with layer conv2d_13: expected ndim=4, found ndim=5
Do you know why did I get these errors? And how to deal with this problem?
I am pulling PNG images from Jupyter Notebooks and manage to display with IPython.display.Image but not with matplotib.pyplot.plt. What am I missing? I use python 2.7.
I am using the following algorithm:
To open the notebook JSON content I do:
import nbformat
notebook_ = nbformat.read(file_notebook, 4)
After retrieving the relevant cell information I pull the png information from it using:
def cell_to_image(cell, out_value_item_number=1):
if "execution_count" in cell.keys(): # i.e version >=4
return cell["outputs"][out_value_item_number]['data']['image/png']
elif "prompt_number" in cell.keys(): # i.e version < 4
return cell["outputs"][out_value_item_number]['png']
return None
cell_image = cell_to_image(cell)
The first few characters of cell_image (which is unicode) looks like:
iVBORw0KGgoAAAANSUhEUgAAA64AAAFMCAYAAADLFeHSAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\n
AAALEgAACxIB0t1+/AAAIABJREFUeJzs3Xd8jef/x/HXyTjZiYQkCGrU3ruR0tr9oq2qGtGo0dbe
\nm5pVlJpFUSMoVb6UoEZ/lCpatWuPUiNEEiMDmef3R75OexonJKUO3s/HI4/mXPd1X/d1f+LRR965
\n7/u6DSaTyYSIiIiIiIiIjbJ70hMQERERERERyYiCq4iIiIiIiNg0BVcRERERERGxaQquIiIiIiIi
\nYtMUXEVERERERMSmKbiKiIiIiIiITVNwFRGRxyIkJIRixYqxfv36+24/e/YsxYoVo3jx4v/yzGxb
\naGgoderUIS4uDoBdu3bRsmVLKlasyCuvvMKgQYOIjo622CcsLIyGDRtSunRp6tSpw8KFC62OW7p0
\naRo2bJju53Lnzh1GjRrFyy+/TNmyZWnRogW//fbbQ835q6++olGjRpQvX5769eszc+ZMkpOTzdtT
\nU1OZNGkSNWrUoHTp0jRp0oTdu3enGyc2NpZOn
I can easily plot in my Jupityer notebook using
from IPython.display import Image
Image(cell_image)
And now to my question:
How can I manipulate cell_image to be plt.subplot friendly?
(Assuming import matplotlib.pyplot as plt).
I realise that plt.imshow wouldn't work because this would require an array, which is not my case (which is a string, as far as I understand).
If you have your image string representation in a variable string_rep, the following code should work.
from io import BytesIO
import matplotlib.image as mpimage
import matplotlib.pyplot as plt
with BytesIO(string_rep.decode('base64')) as byte_rep:
image = mpimage.imread(byte_rep)
plt.imshow(image)
import cv2
import numpy as np
cap = cv2.VideoCapture('traffic.avi')
retval, frame = cap.read()
print retval
================ RESTART: J:\Python For DIP\traffic_video.py ================
False
>>>
The Value of retval is always False, which means the video is not read by the command. It must be True to read frames. I don't know what to do. However when I use my default webcam it turns to be True. I tried many videos and the same problem appears. Note: I have installed the ffmpeg correctly.
Note: This is not the full code, in this step I am only validating cap.read() either True or False
This method is guaranteed 100%
first of all check your version of OpenCV, say for instance 2.4.11. you can check it by typing the following commands in your Python Shell:
>>> from cv2 import __version__
>>> __version__
'2.4.11'
>>>
Then go to C:\opencv\build\x86\vc12\bin and copy opencv_ffmpeg2411.dll.
Finally go to root directory of Python ex: C:\Python27 and paste opencv_ffmpeg2411.dll in it
check the name of the file opencv_ffmpeg2411.dll, whether the version
of opencv is written or not, if not do the following
opencv_ffmpeg(version of your opencv without dots).dll
After that create a new Python file and copy this code and paste it loading your own video
import numpy as np
import cv2
# Capture video from file
cap = cv2.VideoCapture('your video')
while True:
ret, frame = cap.read()
if ret == True:
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
cv2.imshow('frame',gray)
if cv2.waitKey(30) & 0xFF == ord('q'):
break
else:
break
cap.release()
cv2.destroyAllWindows()
you will have an output video for example like this:
Result
Finding the root directory of Python can be a little tricky. I am using an Enthought distribution and, at first, pasted the opencv_ffmpeg file into the wrong Python directory.
WRONG:
C:\Users\USERNAME\AppData\Local\Programs\Python\Python35-32
RIGHT:
C:\Users\USERNAME\AppData\Local\Enthought\Canopy\User
Long story short, make sure you find the right Python directory.