This is a facial recognition app I had created using python , opencv and haar cascade classifier, the app is working good in classifying trained persons, however the app has a problem of detecting unknown persons as a known person who is trained previously , How to fix such problem ?
this is the dataset creation code
import cv2
import os
import time
cam = cv2.VideoCapture(0)
cam.set(3, 640) # set video width
cam.set(4, 480) # set video height
face_detector = cv2.CascadeClassifier('Cascades/haarcascade_frontalface_default.xml')
# For each person, enter one numeric face id
face_id = input('\n enter user id end press <return> ==> ')
print("\n [INFO] Initializing face capture. Look the camera and wait ...")
# Initialize individual sampling face count
count = 0
while(True):
ret, img = cam.read()
img = cv2.flip(img, 1)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_detector.detectMultiScale(gray, 1.3, 5)
width_d, height_d = 150, 150
for (x,y,w,h) in faces:
cv2.rectangle(img, (x,y), (x+w,y+h), (255,0,0), 2)
count += 1
# Save the captured image into the datasets folder
cv2.imwrite("dataset/User." + str(face_id) + '.' + str(count) + ".jpg", cv2.resize(gray[y:y+h,x:x+w] , (width_d, height_d)))
cv2.imshow('image', img)
k = cv2.waitKey(100) & 0xff # Press 'ESC' for exiting video
if k == 27:
break
elif count >= 400: # Take 30 face sample and stop video
break
# Do a bit of cleanup
print("\n [INFO] Exiting Program and cleanup stuff")
cam.release()
cv2.destroyAllWindows()
This is the training phase
import cv2
import numpy as np
from PIL import Image
import os
# Path for face image database
path = 'dataset'
recognizer = cv2.face.LBPHFaceRecognizer_create()
detector = cv2.CascadeClassifier("Cascades/haarcascade_frontalface_default.xml");
# function to get the images and label data
def getImagesAndLabels(path):
width_d, height_d = 150, 150 # Declare your own width and height
imagePaths = [os.path.join(path,f) for f in os.listdir(path)]
faceSamples=[]
ids = []
for imagePath in imagePaths:
PIL_img = Image.open(imagePath).convert('L') # convert it to grayscale
img_numpy = np.array(PIL_img,'uint8')
id = int(os.path.split(imagePath)[-1].split(".")[1])
faces = detector.detectMultiScale(img_numpy)
for (x,y,w,h) in faces:
faceSamples.append(cv2.resize(img_numpy[y:y+h,x:x+w], (width_d, height_d)))
ids.append(id)
return faceSamples,ids
print ("\n [INFO] Training faces. It will take a few seconds. Wait ...")
faces,ids = getImagesAndLabels(path)
recognizer.train(faces, np.array(ids))
# Save the model into trainer/trainer.yml
recognizer.write('trainer/trainer.yml') # recognizer.save() worked on Mac, but not on Pi
# Print the numer of faces trained and end program
print("\n [INFO] {0} faces trained. Exiting Program".format(len(np.unique(ids))))
This is the recognizing phase
import cv2
import numpy as np
import os
recognizer = cv2.face.LBPHFaceRecognizer_create()
recognizer.read('trainer/trainer.yml')
cascadePath = "Cascades/haarcascade_frontalface_default.xml"
faceCascade = cv2.CascadeClassifier(cascadePath);
font = cv2.FONT_HERSHEY_SIMPLEX
#iniciate id counter
id =0
# names related to ids: example ==> Marcelo: id=1, etc
names = ['Mamdouh Alaa' , 'Dr.Ahmed Seddawy' , 'Dr.Ismail Abdulghaffar']
# Initialize and start realtime video capture
cam = cv2.VideoCapture(0)
cam.set(3, 1366) # set video widht
cam.set(4, 768) # set video height[enter image description here][1]
# Define min window size to be recognized as a face
minW = 0.1*cam.get(3)
minH = 0.1*cam.get(4)
while True:
ret, img =cam.read()
img = cv2.flip(img, 1)
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
width_d, height_d = 150, 150
faces = faceCascade.detectMultiScale(
gray,
scaleFactor = 1.2,
minNeighbors = 5,
minSize = (int(minW), int(minH)),
)
for(x,y,w,h) in faces:
cv2.rectangle(img, (x,y), (x+w,y+h), (255,0,0), 2)
id, confidence = recognizer.predict(cv2.resize(gray[y:y+h,x:x+w], (width_d, height_d)))
# Check if confidence is less them 100 ==> "0" is perfect match
if (confidence < 100) :
id = names[id]
confidence = " {0}%".format(round(100 - confidence))
else:
id = "unknown person"
confidence = " {0}%".format(round(100 - confidence))
cv2.putText(img, str(id), (x+5,y-5), font, 1, (255,255,255), 2)
cv2.putText(img, str(confidence), (x+5,y+h-5), font, 1, (255,255,0), 1)
cv2.imshow('IFR',img)
k = cv2.waitKey(10) & 0xff # Press 'ESC' for exiting video
if k == 27:
break
# Do a bit of cleanup
print("\n [INFO] Exiting Program and cleanup stuff")
cam.release()
cv2.destroyAllWindows()
Related
i have an SLR (sign language Recognition) task, and i want to show the preprocessing part, here is my code :
import numpy as np
import cv2
import keras
from keras.preprocessing.image import ImageDataGenerator
from keras.models import load_model
import tensorflow as tf
from tensorflow.compat.v1 import ConfigProto
from tensorflow.compat.v1 import InteractiveSession
config = ConfigProto()
config.gpu_options.allow_growth = True
session = InteractiveSession(config=config)
#Load CNN Model
model = load_model("VGG16withALLTRAINABLE(NO BACKGROUND).h5")
#Creating ROI frame for capturing hand
top_ROI = 100
btm_ROI = 300
right_ROI = 50
left_ROI = 250
#Creating Background Removal Parameters
blur_size = 5
canny_low = 25
# min_area = 0
# max_area = 0
canny_high = 150
dilate_iter = 10
erode_iter = 10
mask_color = (0.0,0.0,0.0)
#Video Capture
cap = cv2.VideoCapture(0)
while True:
ret,frame = cap.read()
#flipping frame
# frame = cv2.flip(frame, 1)
#Create ROI inside Frame
roi = frame[top_ROI:btm_ROI, right_ROI:left_ROI]
cv2.rectangle(frame, (left_ROI, top_ROI), (right_ROI,btm_ROI), (255,128,0), 3) #Visual Rectangle for ROI
#Resizing and Reshaping to equalize model input size and shape
roi = cv2.resize(roi, (300, 300))
blurred_roi = cv2.GaussianBlur(roi, (blur_size,blur_size) , 0)
gray_roi = cv2.cvtColor(blurred_roi, cv2.COLOR_BGR2GRAY)
_,threshed = cv2.threshold(gray_roi, 100, 255, cv2.THRESH_BINARY_INV)
# edge = cv2.Canny(gray_roi, canny_low, canny_high)
# edge = cv2.dilate(edge, None)
# edge = cv2.erode(edge, None)
cntr = []
cntr_area = []
contours,_= cv2.findContours(threshed, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
contour_info = []
for c in contours:
contour_info.append((c,cv2.contourArea(c), ))
contour_info = np.array(contour_info)
contour_info = sorted(contour_info, key=lambda x: x[1], reverse=True)
max_contour = contour_info[0]
mask = np.zeros(threshed.shape)
cv2.fillConvexPoly(mask, max_contour[0], (255))
mask = cv2.dilate(mask, None, iterations=dilate_iter)
mask = cv2.erode(mask, None, iterations=erode_iter)
mask = cv2.GaussianBlur(mask, (blur_size, blur_size), 0)
mask_stack = np.dstack([mask]*3) # Create 3-channel alpha mask
#-- Blend masked img into MASK_COLOR background --------------------------------------
mask_stack = mask_stack.astype('float32') / 255.0 # Use float matrices,
roi = roi.astype('float32') / 255.0 # for easy blending
masked = (mask_stack * roi) + ((1-mask_stack) * mask_color) # Blend
masked = (masked * 255).astype('uint8') # Convert back to 8-bit
print(mask.shape)
print(mask_stack.shape)
print(masked.shape)
cv2.imshow("Frame", frame)
cv2.imshow("ROI", gray_roi)
cv2.imshow("Thresed", threshed)
cv2.imshow('Mask', masked)
key = cv2.waitKey(1)
if key == 27:
break
cap.release()
cv2.destroyAllWindows()
This is my current result [Result in diffrent Frames]
My question is, can i make all the result in one frames (one frame with multiple videos) ?
i have tried once with this code, but it wont work while i add the second video stream functions (video_stream2()) :
from tkinter import *
from PIL import ImageTk, Image
import cv2
#Creating ROI frame for capturing hand
top_ROI = 100
btm_ROI = 300
right_ROI = 50
left_ROI = 250
root = Tk()
root.geometry("1920x1080")
# Create a frame
Main_video = Frame(root, highlightbackground='grey', highlightthicknes=3)
Main_video.grid(row=0, column= 0, padx=450, pady=150, ipadx= 0, ipady=0)
Roi_video = Frame(root, highlightbackground='grey', highlightthicknes=3)
Roi_video.grid(row=0, column= 0, padx=0, pady=0, ipadx= 0, ipady=0)
# Create a label in the frame
label_main = Label(Main_video)
label_main.grid()
label_roi = Label(Roi_video)
label_roi.grid()
# Capture from camera
cap = cv2.VideoCapture(0)
# function for video streaming
def video_stream():
_, frame = cap.read()
#Create ROI inside Frame
cv2image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
#Main Video
img = Image.fromarray(cv2image)
imgtk = ImageTk.PhotoImage(image=img)
label_main.imgtk = imgtk
label_main.configure(image=imgtk)
label_main.after(1, video_stream)
def video_stream2():
_, frame = cap.read()
#Create ROI inside Frame
roi = frame[top_ROI:btm_ROI, right_ROI:left_ROI]
cv2.rectangle(frame, (left_ROI, top_ROI), (right_ROI,btm_ROI), (255,128,0), 3) #Visual Rectangle for ROI
cv2roi_gray = cv2.cvtColor(roi, cv2.COLOR_RGB2GRAY)
#Roi Video
roi_img = Image.fromarray(cv2roi_gray)
imgtk_roi= ImageTk.PhotoImage(image=roi_img)
label_roi.imgtk_roi = imgtk_roi
label_roi.configure(image=imgtk_roi)
label_roi.after(1, video_stream2)
video_stream()
video_stream2()
root.mainloop()
The procedure to combine several images (windows) to one like that:
...is easy by following the example code:
import numpy as np
import cv2
import time
#Video Capture
cap = cv2.VideoCapture(0)
while(True):
ret,frame = cap.read()
frame_uus=cv2.resize(frame,(240,160))
#let's simulate the images...
#frame=np.random.randint(0,255,[320,480,3],dtype='uint8')
gray_roi=0.5*np.random.randint(0,255,[160,240,1],dtype='uint8')+0.5*frame_uus[:,:,0:1]
threshed=0.1+0*np.random.randint(0,255,[160,240,3],dtype='uint8')+0.3*frame_uus
masked=0.5*np.random.randint(0,255,[160,240,3],dtype='uint8')+0.2*frame_uus
#make sure all data is in uint8-format suitable for cv2..
gray_roi=gray_roi.astype(np.uint8)
threshed=threshed.astype(np.uint8)
masked=masked.astype(np.uint8)
#show separate images...
cv2.imshow("Frame", frame)
cv2.imshow("ROI", gray_roi)
cv2.imshow("Thresed", threshed)
cv2.imshow('Mask', masked)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
#Define space between images...
vali=2
#let's combine the images...
max_height=np.max([len(frame),len(gray_roi),len(threshed),len(masked)])
#Let's calculate total width for the combined image...remember to add space between images...
total_width=len(frame[0])+len(gray_roi[0])+len(threshed[0])+len(masked[0])+4*vali
#For clearness let's make a green background image
baseimage=np.zeros([max_height,total_width,3],'uint8')
baseimage[:,:,1]=255
#let's add separate images to the baseimage
baseimage[0:len(frame),0:len(frame[0]),:]=frame
#Take into account the grayscale...
alku=len(frame[0])+vali
loppu=alku+len(gray_roi[0])
baseimage[0:len(gray_roi),alku:loppu,0:1]=gray_roi
baseimage[0:len(gray_roi),alku:loppu,1:2]=gray_roi
baseimage[0:len(gray_roi),alku:loppu,2:3]=gray_roi
#Add next image...
alku=loppu+vali
loppu=alku+len(threshed[0])
baseimage[0:len(threshed),alku:loppu,:]=threshed
#And the last one...
alku=loppu+vali
loppu=alku+len(masked[0])
baseimage[0:len(masked),alku:loppu,:]=masked
#And finally let's show the baseimage...
cv2.imshow('Combined', baseimage)
cap.release()
cv2.destroyAllWindows()
I was trying to capture am image on the webcam and extract the text information on it using the language of python.
Here is the code:
import cv2
import matplotlib.pyplot as plt
import numpy as np
import pytesseract
from PIL import Image
from pytesseract import image_to_string
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
def main():
# Use the attached camera to capture images
# 0 stands for the first one
cap = cv2.VideoCapture(0)
if cap.isOpened():
ret, frame = cap.read()
print(ret)
print(frame)
else:
ret = False
img1 = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
# img = Image.open('image.jpg')
text = pytesseract.image_to_string(img1)
print(text)
# plt.imshow(img1)
# plt.title('Color Image RGB')
# plt.xticks([])
# plt.yticks([])
# plt.show()
cap.release()
if __name__ == "__main__":
main()
The code didn't work. I watched a couple of videos on Youtube, and I saw that people typically use Image.open("image.jpg") to open an image that is located on the computer. But I need to capture the image from the webcam and extract the information on it. So that method won't work in my situation. Is there a way to combine these two methods? Like capture the image using cv2 and extract the information using pytesseract.image_to_string()?
Can you please try by replacing the below code of line,
text = pytesseract.image_to_string(img1)
With the code,
text = pytesseract.image_to_string(Image.fromarray(img1))
Or have a working code snippet here, (Copied your code and updated a little),
def main():
# Use the attached camera to capture images
# 0 stands for the first one
cap = cv2.VideoCapture(0)
while cap.isOpened():
ret, frame = cap.read()
img1 = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
text = pytesseract.image_to_string(Image.fromarray(img1))
cv2.imshow('frame', img1)
if cv2.waitKey(0) & 0xFF == ord('q'):
return None
print("Extracted Text: ", text)
cap.release()
Hope This will help you.
I used while look because with if condtion I did not get result, trying to figure it out.
import cv2
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'
framewidth = 640
frameheight = 480
cap = cv2.VideoCapture(0)
cap.set(3, framewidth)
cap.set(4, frameheight)
while True:
success, img = cap.read( )
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# print(pytesseract.image_to_string(img))
## detecting characters
# hImg,wImg,_= img.shape
# boxes=pytesseract.image_to_boxes(img)
# for b in boxes.splitlines():
# # print(b)
# b=b.split(' ')
# print(b)
# x,y,w,h = int(b[1]),int(b[2]),int(b[3]),int(b[4])
# cv2.rectangle(img,(x,hImg-y),(w,hImg-h),(0,0,255),3)
# cv2.putText(img,b[0],(x,hImg-y+25),cv2.FONT_HERSHEY_COMPLEX,1,(50,100,255),2)
# ## detecting words
hImg, wImg, _ = img.shape
boxes = pytesseract.image_to_data(img)
for x, b in enumerate(boxes.splitlines( )):
if x != 0:
b = b.split( )
print(b)
if len(b)==12:
x, y, w, h = int(b[6]), int(b[7]), int(b[8]), int(b[9])
cv2.rectangle(img, (x, y), (w+x, h+y), (0, 0, 255), 3)
cv2.putText(img, b[11], (x, y), cv2.FONT_HERSHEY_COMPLEX, 1, (50, 100, 255), 2)
## detecting digits
# hImg, wImg, _ = img.shape
# cong= r'--oem 3 --psm 6 outputbase digits'
# boxes = pytesseract.image_to_data(img,config=cong)
#
# for x, b in enumerate(boxes.splitlines( )):
#
# if x != 0:
# b = b.split( )
# print(b)
# if len(b) == 12:
# x, y, w, h = int(b[6]), int(b[7]), int(b[8]), int(b[9])
# cv2.rectangle(img, (x, y), (w + x, h + y), (0, 0, 255), 3)
# cv2.putText(img, b[11], (x, y), cv2.FONT_HERSHEY_COMPLEX, 1, (50, 100, 255), 2)
# reading text don't delete it
# print(pytesseract.image_to_boxes(img))
cv2.imshow("video", img)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
#I don't no how to give answer but i have my code and it's working fine enjoy
Using Opencv to make a face recognition
This is the code I am using to recognize faces in my webcam, but once the camera do not recognize a face, it is stopping to record and I want it countinuous.
import cv2
import logging as log
from time import sleep
import datetime as dt
import numpy as np
cascPath = "haarcascade_frontalface_default.xml"
faceCascade = cv2.CascadeClassifier(cascPath)
cam = cv2.VideoCapture(0);
anterior = 0
log.basicConfig(filename='webcam.log',level=log.INFO)
rec = cv2.face.LBPHFaceRecognizer_create();
rec.read('recognizer/trainningData.yml')
id=0
font = cv2.FONT_HERSHEY_SIMPLEX
fontscale = 1
fontcolor = (255,255,255)
while(True):
if not cam.isOpened():
print('Unable to load camera.')
sleep(5)
pass
ret, img = cam.read();
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = faceCascade.detectMultiScale(gray, scaleFactor=1.1,minNeighbors=5,minSize=(30, 30))
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(id == 1):
id = "Nome do usuário detectado";
cv2.putText(img,str(id),(x,y-10),font,0.55,(0,255,0),1);
cv2.imshow("Face", img);
if(conf<=20):
if(id!=None):
cv2.putText(img,str(id),(x,y-10),font,0.55,(0,255,0),1);
else:
cv2.putText(img,"Unknown",(x,y+h-10),font,0.55, (0,255,0),1);
if anterior != len(faces):
anterior = len(faces)
log.info("ID: " + str(id) + " faces: "+str(len(faces))+" at "+str(dt.datetime.now()))
if(cv2.waitKey(1)==ord('q')):
break;
cam.release()
cv2.destroyAllWindows()
Look at your code closely...you're calling imshow() method, which is responsible for showing the image, inside the for loop that is processing the detected faces.
This means that if faces are not detected, then that for loop is not executed, and thus imshow() is not called.
If you want to show the image regardless of detection result, move imshow() call to the while loop
I have done tons of research into this , and I think my logic are worn out , almost there but can't seem to understand why nothing is display in the cv2.imshow() windows just a grey box , however good news is I am able to detect a face and crop that face then save it in the folder.
can you please shed some light of where I have gone wrong
#Author: Waheed Rafiq
#Research Student Birmingham City University
#Date: 03/11/2016
#Description :detect and Save capture face in a folder.
#Import library required for Capture face.
import cv2
#import the cascade for face detection
FaceClassifier =cv2.CascadeClassifier
('haarcascade_frontalface_default.xml')
# access the webcam (every webcam has
capture = cv2.VideoCapture(0)
while(True):
# Capture frame-by-frame
ret, frame = capture.read()
if not capture:
print "Error opening webcam device"
sys.exit(1)
# to detect faces in video
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = FaceClassifier.detectMultiScale(gray, 1.3, 5)
# Resize Image
minisize = (frame.shape[1],frame.shape[0])
miniframe = cv2.resize(frame, minisize)
# Store detected frames in variable name faces
faces = FaceClassifier.detectMultiScale(miniframe)
# Draw rectangle
for f in faces:
x, y, w, h = [ v for v in f ]
cv2.rectangle(frame, (x,y), (x+w,y+h), (255,255,255))
#Save just the rectangle faces in SubRecFaces
sub_face = frame[y:y+h, x:x+w]
FaceFileName = "unknowfaces/face_" + str(y) + ".jpg"
cv2.imwrite(FaceFileName, sub_face)
#Display the image
cv2.imshow('Result',frame)
break
# When everything done, release the capture
img.release()
cv2.waitKey(20)
cv2.destroyAllWindows()
really would appericate your support
I had to revamp my code , and re-think the logics again: for those of you who wish to know how to detect a face from webcam or Raspberry PI using Opencv and then crop that detected face this is how you do it in python 2.7 using OpenCV 2.4.12
# croppfacedetection.py
#Author: Waheed Rafiq
#Research Student Birmingham City University
#Date: 03/11/2016
#Description : Save capture face in a folder.
#Import library required for Capture face.
# Should you wish to use this code for
#education purpose in your assignment or dissertation
# please use the correct citation and give credit where required.
import cv2
size = 4
webcam = cv2.VideoCapture(0) #Use camera 0
# We load the xml file
classifier = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
# Above line normalTest
#classifier = cv2.CascadeClassifier('haarcascade_frontalface_alt.xml')
#Above line test with different calulation
#classifier = cv2.CascadeClassifier('haarcascade_frontalface_alt_tree.xml')
#classifier = cv2.CascadeClassifier('lbpcascade_frontalface.xml')
while True:
(rval, im) = webcam.read()
im=cv2.flip(im,1,0) #Flip to act as a mirror
# Resize the image to speed up detection
mini = cv2.resize(im, (im.shape[1] / size, im.shape[0] / size))
# detect MultiScale / faces
faces = classifier.detectMultiScale(mini)
# Draw rectangles around each face
for f in faces:
(x, y, w, h) = [v * size for v in f] #Scale the shapesize backup
cv2.rectangle(im, (x, y), (x + w, y + h),(0,255,0),thickness=4)
#Save just the rectangle faces in SubRecFaces
sub_face = im[y:y+h, x:x+w]
FaceFileName = "unknowfaces/face_" + str(y) + ".jpg"
cv2.imwrite(FaceFileName, sub_face)
# Show the image
cv2.imshow('BCU Research by Waheed Rafiq (c)', im)
key = cv2.waitKey(10)
# if Esc key is press then break out of the loop
if key == 27: #The Esc key
break
remember you will need to create a folder and within that area you will need a folder named unknownfaces run the script from root of the folder and it should save any faces it detects into unknowfaces folder.
further information about this code will be available soon my site
waheedrafiq.net
It's the 'working' version of the code with Python 3.6 OpenCV 4+. You don't have to refer anyone, use it freely.
import cv2
import os
classifier = cv2.CascadeClassifier(cv2.data.haarcascades+"haarcascade_frontalface_default.xml")
dirFace = 'cropped_face'
# Create if there is no cropped face directory
if not os.path.exists(dirFace):
os.mkdir(dirFace)
print("Directory " , dirFace , " Created ")
else:
print("Directory " , dirFace , " has found.")
webcam = cv2.VideoCapture(0) # Camera 0 according to USB port
# video = cv2.VideoCapture(r"use full windows path") # video path
while (True):
(f, im) = webcam.read() # f returns only True, False according to video access
# (f, im) = video.read() # video
if f != True:
break
# im=cv2.flip(im,1,0) #if you would like to give mirror effect
# detectfaces
faces = classifier.detectMultiScale(
im, # stream
scaleFactor=1.10, # change these parameters to improve your video processing performance
minNeighbors=20,
minSize=(30, 30) # min image detection size
)
# Draw rectangles around each face
for (x, y, w, h) in faces:
cv2.rectangle(im, (x, y), (x + w, y + h),(0,0,255),thickness=2)
# saving faces according to detected coordinates
sub_face = im[y:y+h, x:x+w]
FaceFileName = "cropped_face/face_" + str(y+x) + ".jpg" # folder path and random name image
cv2.imwrite(FaceFileName, sub_face)
# Video Window
cv2.imshow('Video Stream',im)
key = cv2.waitKey(1) & 0xFF
# q for exit
if key == ord('q'):
break
webcam.release()
It looks like cv2.waitKey(20) is not reached by your code. You should move it before the break statement.
In OpenCV cv2.waitKey completes the image display task. It is not just for adding a pause.
I have to track a window in a video and need to paste an image on window,I have used camshift to track the window, but it did not track it correct.My window is in brown color so I have given the following color range.
np.array((110,0,0)--lower
np.array((130,255,255)--higher..
I have red many documents in opencv but not able to figure out which method to follow.I am using opencv2.4.9 with python.
Below is the code which I tried.Please help me out to figure out the exact location of window.emphasized text
#!/usr/bin/env python
import numpy as np
import cv2
cap = cv2.VideoCapture("myvideo.mp4")
# take first frame of the video
ret,frame = cap.read()
#print frame
#print ret
# setup initial location of window
r,h,c,w = 157,40,337,40
track_window = (c,r,w,h)
# set up the ROI for tracking
roi = frame[r:r+h, c:c+w]
hsv_roi = cv2.cvtColor(roi, cv2.COLOR_BGR2HSV)
mask = cv2.inRange(hsv_roi, np.array((110,0,0)), np.array((130,255,255)))
roi_hist = cv2.calcHist([hsv_roi],[0],mask,[255],[0,255])
cv2.imshow('img2',roi_hist)
#print roi_hist
cv2.normalize(roi_hist,roi_hist,0,255,cv2.NORM_MINMAX)
# Setup the termination criteria, either 10 iteration or move by at least 1 pt
term_crit = ( cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, 10, 1 )
i = 1
while(1):
ret ,frame = cap.read()
if ret == True:
i += 1
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
dst = cv2.calcBackProject([hsv],[0],roi_hist,[0,255],1)
# apply meanshift to get the new location
ret, track_window = cv2.CamShift(dst, track_window, term_crit)
#print track_window
# Draw it on image
x,y,w,h = track_window
img2 = cv2.rectangle(frame, (x,y), (x+w,y+h), 255,2)
cv2.imshow('img2',frame)
k = cv2.waitKey(200) & 0xff
if k == 27:
break
else:
# print "comes here2";
cv2.imwrite(str(i)+"test.jpg",frame)
#break
else:
break
cv2.destroyAllWindows()
cap.release()