I'm new to Python but want to learn it a bit so I decided to create a program
with template matching from desktop input.
Can any one help with this ? How to write template matching with stream from desktop ?
import time
import cv2
import mss
import numpy
template = cv2.imread('template.jpg', 0)
w, h = template.shape[::-1]
with mss.mss() as sct:
# Part of the screen to capture
monitor = {"top": 40, "left": 0, "width": 800, "height": 640}
while "Screen capturing":
last_time = time.time()
# Get raw pixels from the screen, save it to a Numpy array
img = numpy.array(sct.grab(monitor))
# Display the picture
# cv2.imshow("OpenCV/Numpy normal", img)
# Display the picture in grayscale
cv2.imshow('OpenCV/Numpy grayscale', cv2.cvtColor(img, cv2.COLOR_BGRA2GRAY))
# Print fps
print("fps: {}".format(1 / (time.time() - last_time)))
# Search template in stream
# Press "q" to quit
if cv2.waitKey(25) & 0xFF == ord("q"):
cv2.destroyAllWindows()
break
The first thing I noticed that you did not apply any edge-detection to your template image. The edge-detection is not necessary but useful for finding the features of the template image.
Assume I have the following image:
To detect the above template image precisely I should be applying an edge detection algorithm.
template = cv2.imread("three.png")
template = cv2.cvtColor(template, cv2.COLOR_BGR2GRAY)
template = cv2.Canny(template, 50, 200)
I should also apply edge detection to the stream from desktop.
img = sct.grab(mon)
gray = cv2.cvtColor(np.array(img), cv2.COLOR_BGR2GRAY)
edged = cv2.Canny(gray, 50, 200)
Check if the template matches with the captured image
result = cv2.matchTemplate(edged, template, cv2.TM_CCOEFF)
(_, maxVal, _, maxLoc) = cv2.minMaxLoc(result)
If template image matched in the stream from desktop then get the coordinates.
(_, maxLoc, r) = found
(startX, startY) = (int(maxLoc[0] * r), int(maxLoc[1] * r))
(endX, endY) = (int((maxLoc[0] + w) * r), int((maxLoc[1] + h) * r))
Finally draw the rectangle for displaying the location:
cv2.rectangle(img, (startX, startY), (endX, endY), (180, 105, 255), 2)
Result:
From above we see that the our template 3 value is matched on the stream from desktop.
Code:
import time
import cv2
import numpy as np
import imutils
from mss import mss
template = cv2.imread("three.png")
template = cv2.cvtColor(template, cv2.COLOR_BGR2GRAY)
template = cv2.Canny(template, 50, 200)
(h, w) = template.shape[:2]
start_time = time.time()
mon = {'top': 200, 'left': 200, 'width': 200, 'height': 200}
with mss() as sct:
while True:
last_time = time.time()
img = sct.grab(mon)
img = np.array(img)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
edged = cv2.Canny(gray, 50, 200)
found = None
for scale in np.linspace(0.2, 1.0, 20)[::-1]:
resized = imutils.resize(gray, width=int(gray.shape[1] * scale))
r = gray.shape[1] / float(resized.shape[1])
if resized.shape[0] < h or resized.shape[1] < w:
break
edged = cv2.Canny(resized, 50, 200)
cv2.imwrite("canny_image.png", edged)
result = cv2.matchTemplate(edged, template, cv2.TM_CCOEFF)
(_, maxVal, _, maxLoc) = cv2.minMaxLoc(result)
if found is None or maxVal > found[0]:
found = (maxVal, maxLoc, r)
(_, maxLoc, r) = found
(startX, startY) = (int(maxLoc[0] * r), int(maxLoc[1] * r))
(endX, endY) = (int((maxLoc[0] + w) * r), int((maxLoc[1] + h) * r))
cv2.rectangle(img, (startX, startY), (endX, endY), (180, 105, 255), 2)
print('The loop took: {0}'.format(time.time()-last_time))
cv2.imshow('test', np.array(img))
if cv2.waitKey(25) & 0xFF == ord('q'):
cv2.destroyAllWindows()
break
Let untitled.png be a file storing the image
Here is a working program. I used the following to put it together,
OpenCV Org: Template Matching
Taking screenshots with OpenCV and Python
OpenCV python: ValueError: too many values to unpack
import os
import cv2 as cv
import numpy as np
import pyautogui
import time
import winsound # for sound
from matplotlib import pyplot as plt
os.chdir("C:\\Users\\Mike\\\Desktop")
img = cv.imread('untitled.png',0)
img_piece = cv.cvtColor(img, cv.COLOR_RGB2BGR)
c, w, h = img_piece.shape[::-1]
while 1:
pic = pyautogui.screenshot()
template = cv.cvtColor(np.array(pic), cv.COLOR_RGB2BGR)
meth = 'cv.TM_CCOEFF'
method = eval(meth)
# Apply template Matching
res = cv.matchTemplate(img_piece,template,method)
min_val, max_val, min_loc, max_loc = cv.minMaxLoc(res)
top_left = max_loc
bottom_right = (top_left[0] + w, top_left[1] + h)
cv.rectangle(img,top_left, bottom_right, 255, 2)
if max_val > 66000000.0:
print(max_val, top_left, bottom_right)
winsound.Beep(888, 111)
if 1:
plt.subplot(121),plt.imshow(res,cmap = 'gray')
plt.title('Matching Result'), plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(img,cmap = 'gray')
plt.title('Detected Point'), plt.xticks([]), plt.yticks([])
plt.suptitle(meth)
plt.show()
break
time.sleep(1)
Below is the basic code to perform a match template. Place it below img = numpy.array(sct.grab(monitor)) and it will run every frame.
# create grayscale of image - because template is also grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# perform match
res = cv2.matchTemplate(gray,template ,cv2.TM_CCOEFF)
# get coordinates of best match
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(res)
top_left = min_loc
bottom_right = (top_left[0] + w, top_left[1] + h)
# draw red rectangle over original screen capture
cv2.rectangle(img,top_left, bottom_right,(0,0,255),3)
# display image
cv2.imshow('Result',img)
You can find some more info on matchTemplate here
Related
I am trying to do background subtraction using MOG2, It was working fine, but when there is deep shadow of a moving object then the shadow is considered as foreground object and I don't want that shadow as foreground object (I'm running MOG2 for 13 images). How can I remove these shadow so that it does not come in foreground?
Here is a sample image...
original img
image after applying MOG2
here is my sample code...
import os
import numpy as np
import cv2
import glob
import imutils
i=0
bg_flag = 0
image_list = []
bgs_list = []
#bgsfinal function
def detection(image_list):
global i
global bg_flag
bgs3_img = None
backsub = cv2.createBackgroundSubtractorMOG2(128, cv2.THRESH_BINARY, 1)
print("start2")
for k in range(len(image_list)):
frame = image_list[k]
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
cv2.imwrite('./gray/'+str(k)+'.jpg', frame)
#blur = cv2.medianBlur(frame, 21)
blur = frame
bgs_list.append(blur)
for bg in range(len(bgs_list)):
rects = []
#start_time = time.time()
frame_blur = bgs_list[bg]
img = image_list[bg].copy()
s_frame = image_list[bg]
new_frame = s_frame.copy()
fgmask = backsub.apply(frame_blur)
cv2.imwrite("./bgs/"+str(i)+".jpg", fgmask)
fgmask[fgmask==127] = 0
cv2.imwrite("./dilate/"+str(i)+".jpg", fgmask)
thresh = cv2.threshold(fgmask, 128, 255, cv2.THRESH_BINARY)[1]
thresh = cv2.erode(thresh, None, iterations = 1)
thresh = cv2.dilate(thresh, None, iterations=1)
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
for c in cnts:
#M = cv2.moments(c)
A = cv2.contourArea(c)
(x, y, w, h) = cv2.boundingRect(c)
cv2.rectangle(new_frame, (x, y), (x + w, y + h), (0,0, 255), 1)
cv2.putText(new_frame, str(A), (x - 10, y - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 1)
cv2.imwrite("./area/"+str(i)+".jpg", new_frame)
cv2.rectangle(thresh, (x, y), (x + w, y + h), (255,255, 255), 1)
cv2.putText(thresh, str(A), (x - 10, y - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 1)
cv2.imwrite("./area_bgs/"+str(i)+".jpg", thresh)
i+=1
print("Done!")
#this folder contains 13 continuous images
images = glob.glob('./inci4/*.jpg')
for j in range(len(images)):
img = cv2.imread(images[j])
img = cv2.resize(img, (360, 640))
image_list.append(img)
detection(image_list)
I am trying to use opencv to create a rectangle around a cone. Where I am currently at is I have outlined the code which has resulted in a triangle shape. How can I use opencv to create a rectangle around the triangle.
My code so far:
import cv2
import numpy as np
img = cv2.imread('image.jpg')
ret, mask = cv2.threshold(img[:, :,2], 235, 255, cv2.THRESH_BINARY)
mask3 = np.zeros_like(img)
mask3[:, :, 0] = mask
mask3[:, :, 1] = mask
mask3[:, :, 2] = mask
orange = cv2.bitwise_and(img, mask3)
cv2.imwrite("output.jpg", orange)
im = cv2.imread('output.jpg')
imgray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 127, 255, 0)
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(im, contours, -1, (0,255,0), 3)
cv2.imshow('img',im)
cv2.waitKey(0)
cv2.destroyAllWindows
Jpeg File:
One approach is using multi-scale template matching
You crop the object you want to find:
Apply Canny edge-detection to find the edges
edged = cv2.Canny(resized, 50, 200)
Find the matched template using matchTemplate
result = cv2.matchTemplate(edged, template, cv2.TM_CCOEFF)
Result:
Code:
import numpy as np
import imutils
import glob
import cv2
template = cv2.imread("template.jpg")
template = cv2.cvtColor(template, cv2.COLOR_BGR2GRAY)
template = cv2.Canny(template, 50, 200)
(h, w) = template.shape[:2]
for imagePath in glob.glob("img2" + "/pXobJ.jpg"):
image = cv2.imread(imagePath)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
found = None
for scale in np.linspace(0.2, 1.0, 20)[::-1]:
resized = imutils.resize(gray, width=int(gray.shape[1] * scale))
r = gray.shape[1] / float(resized.shape[1])
if resized.shape[0] < h or resized.shape[1] < w:
break
edged = cv2.Canny(resized, 50, 200)
result = cv2.matchTemplate(edged, template, cv2.TM_CCOEFF)
(_, maxVal, _, maxLoc) = cv2.minMaxLoc(result)
if found is None or maxVal > found[0]:
found = (maxVal, maxLoc, r)
(_, maxLoc, r) = found
(startX, startY) = (int(maxLoc[0] * r), int(maxLoc[1] * r))
(endX, endY) = (int((maxLoc[0] + w) * r), int((maxLoc[1] + h) * r))
cv2.rectangle(image, (startX, startY), (endX, endY), (0, 0, 255), 2)
cv2.imwrite("img2/out.jpg", image)
print("Table coordinates: ({}, {}, {}, {})".format(startX, startY, endX, endY))
You can also use deep learning object detection with trained networks.
I have done multi-scale template matching in real-time from looking at this article. When the template appears in the frame, it detects it and drawing a bounding box around it which means it works fine. But when there is no template in the frame also, it detects somewhere and drawing the bounding box. I'll mention the code and the error that I recognized.
import cv2 as cv2
import numpy as np
import imutils
def main():
template1 = cv2.imread("C:\\Users\\Manthika\\Desktop\\opencvtest\\template.jpg")
template1 = cv2.cvtColor(template1, cv2.COLOR_BGR2GRAY)
template1 = cv2.Canny(template1, 50, 200)
template = imutils.resize(template1, width=60)
(tH, tW) = template.shape[:2]
cv2.imshow("Template", template)
windowName = "Something"
cv2.namedWindow(windowName)
cap = cv2.VideoCapture(0)
if cap.isOpened():
ret, frame = cap.read()
else:
ret = False
# loop over the frames to find the template
while ret:
# load the image, convert it to grayscale, and initialize the
# bookkeeping variable to keep track of the matched region
ret, frame = cap.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
found = None
# loop over the scales of the image
for scale in np.linspace(0.2, 1.0, 20)[::-1]:
# resize the image according to the scale, and keep track
# of the ratio of the resizing
resized = imutils.resize(gray, width=int(gray.shape[1] * scale))
r = gray.shape[1] / float(resized.shape[1])
# if the resized image is smaller than the template, then break
# from the loop
if resized.shape[0] < tH or resized.shape[1] < tW:
print("frame is smaller than the template")
break
# detect edges in the resized, grayscale image and apply template
# matching to find the template in the image
edged = cv2.Canny(resized, 50, 200)
result = cv2.matchTemplate(edged, template, cv2.TM_CCOEFF)
(_, maxVal, _, maxLoc) = cv2.minMaxLoc(result)
# if we have found a new maximum correlation value, then update
# the bookkeeping variable
if found is None or maxVal > found[0]:
found = (maxVal, maxLoc, r)
# unpack the bookkeeping variable and compute the (x, y) coordinates
# of the bounding box based on the resized ratio
# print(found)
if found is None:
# just show only the frames if the template is not detected
cv2.imshow(windowName, frame)
print("No template is found")
else:
(_, maxLoc, r) = found
(startX, startY) = (int(maxLoc[0] * r), int(maxLoc[1] * r))
(endX, endY) = (int((maxLoc[0] + tW) * r), int((maxLoc[1] + tH) * r))
print(startX, startY, endX, endY)
# draw a bounding box around the detected result and display the image
cv2.rectangle(frame, (startX, startY), (endX, endY), (0, 0, 255), 2)
cv2.imshow(windowName, frame)
if cv2.waitKey(1) == 27:
break
cv2.destroyAllWindows()
cap.release()
if __name__ == "__main__":
main()
I think the problem is in this two lines,
if found is None or maxVal > found[0]:
found = (maxVal, maxLoc, r)
found variable always updates with a value even if it is none. I'm new to computer vision so please be kind and help me to solve this problem. And also kindly let me know if I need to mention anything else. Thank you.
Refer to How do I use OpenCV MatchTemplate?:
In your code, you have (_, maxVal, _, maxLoc) = cv2.minMaxLoc(result), where it should be minVal,maxVal,minLoc,maxLoc = cv.MinMaxLoc(result), and you need to set a threshold of minVal to filter unmatched results.
Example:
# loop over the scales of the image
for scale in np.linspace(0.2, 1.0, 20)[::-1]:
# resize the image according to the scale, and keep track
# of the ratio of the resizing
resized = imutils.resize(gray, width=int(gray.shape[1] * scale))
r = gray.shape[1] / float(resized.shape[1])
# if the resized image is smaller than the template, then break
# from the loop
if resized.shape[0] < tH or resized.shape[1] < tW:
break
# detect edges in the resized, grayscale image and apply template
# matching to find the template in the image
edged = cv2.Canny(resized, 50, 200)
result = cv2.matchTemplate(edged, template, cv2.TM_CCOEFF)
(minVal, maxVal, _, maxLoc) = cv2.minMaxLoc(result)
# if we have found a new maximum correlation value, then ipdate
# the bookkeeping variable
if found is None or maxVal > found[0]:
found = (maxVal, maxLoc, r)
# unpack the bookkeeping varaible and compute the (x, y) coordinates
# of the bounding box based on the resized ratio
(maxVal, maxLoc, r) = found
# Threshold setting, this 11195548 value is tested by some random images
threshold = 11195548
if maxVal > threshold:
print("match found")
(startX, startY) = (int(maxLoc[0] * r), int(maxLoc[1] * r))
(endX, endY) = (int((maxLoc[0] + tW) * r), int((maxLoc[1] + tH) * r))
# draw a bounding box around the detected result and display the image
cv2.rectangle(image, (startX, startY), (endX, endY), (0, 0, 255), 2)
cv2.imshow("Image", image)
cv2.waitKey(0)
else:
print("no match found")
I am having problems getting face detection and cropping an image to the face working, below is my code.
import cv2
class Crop:
#constructor
def __init__(self, image):
self.data = image
def facechop(self):
# read xml for training data
facedata = "haarcascade_frontalface_default.xml"
cascade = cv2.CascadeClassifier(facedata)
# read image file
img = cv2.imread(self.data, 0)
minisize = (img.shape[1], img.shape[0])
miniframe = cv2.resize(img, minisize)
faces = cascade.detectMultiScale(miniframe)
for f in faces:
x, y, w, h = [ v for v in f ]
cv2.rectangle(img, (x, y), (x + w, y + h), (255, 255, 255))
sub_face = self.data[y:y + h, x:x + w]
# Show picture
cv2.imshow('img', sub_face)
return
input image file
picture = 'izz.jpg'
pic = Crop(gambar)
pic.facechop()
# keyboard input to destroy the window
while(True):
key = cv2.waitKey(0)
if key in [27, ord('Q'), ord('q')]:
break
when it's running, it doesn't do raw after for function till sub_face = self.data[y:y + h, x:x + w]. It directly goes to cv2.imshow('img', sub_face). So, sub_face is not known. Why does it not work well?
I'm using Aptana to debug it. Thank you.
Try changing your code to as follows:
import cv2
def crop(img):
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
sub_face = img
faces = face_cascade.detectMultiScale(img, 1.1, 5)
for (x,y,w,h) in faces:
sub_face = img[y:y+h, x:x+w]
return sub_face
imageToCrop = cv2.imread('izz.jpg',0)
croppedImage = crop(imageToCrop)
cv2.imshow('img',croppedImage)
cv2.waitKey(0)
cv2.destroyAllWindows()
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'