Here is my code
def get_screen(hwnd, zoom=1):
left, top, right, bot = [round(zoom*x) for x in win32gui.GetWindowRect(hwnd)]
width = right - left
height = bot - top
hwindc = win32gui.GetWindowDC(hwnd)
srcdc = win32ui.CreateDCFromHandle(hwindc)
memdc = srcdc.CreateCompatibleDC()
bmp = win32ui.CreateBitmap()
bmp.CreateCompatibleBitmap(srcdc, width, height)
memdc.SelectObject(bmp)
memdc.BitBlt((0, 0), (width, height), srcdc, (0, 0), win32con.SRCCOPY)
signedIntsArray = bmp.GetBitmapBits(True)
img = np.frombuffer(signedIntsArray, dtype='uint8')
img.shape = (height,width,4)
srcdc.DeleteDC()
memdc.DeleteDC()
win32gui.ReleaseDC(hwnd, hwindc)
win32gui.DeleteObject(bmp.GetHandle())
return cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
hwnd_list = []
def get_all_hwnd(hwnd,mouse):
if win32gui.IsWindow(hwnd) and win32gui.IsWindowEnabled(hwnd) and win32gui.IsWindowVisible(hwnd):
if(win32gui.GetWindowText(hwnd)=='梦幻西游三维版模拟器'):
hwnd_list.append(hwnd)
win32gui.EnumWindows(get_all_hwnd, 0)
hwnd = [hwnd_list[0]] # [hwnd_list[0]]
for hwnd in hwnd_list:
rect = win32gui.GetWindowRect(hwnd)
win32gui.MoveWindow(hwnd, rect[0], rect[1], 768, 461,True)
win32gui.SetBkMode(hwnd, win32con.TRANSPARENT)
img1 = get_screen(hwnd)
get = cv2.imread('D:/Code/template/get.jpg', 0)
cv2.matchTemplate(img1,get,cv2.TM_CCOEFF_NORMED).max()
This code works fine on the computer A (the similiarity can be up to 0.9), where templates were obtained. But when I run this code on computer B, the similiarity is only 0.5. I use the same template on computer B and only the screenshots are different. I belive this issue is caused by function get_screen.
Here is an example of screenshot
enter image description here
I expect the similarity in computer B is also above 0.9.
Good evening! I need a global variable in a function to be used in another function, however, when I try to declare this variable as a global variable, it throws the error "Statement expected, found Py:EQ", this in the line where the global code snippet is id, confidence = recognizer.predict(faceimage) specifically above the = sign on line 53. How do I fix this error?
# install opencv "pip install opencv-python"
import cv2
# distance from camera to object(face) measured
# centimeter
Known_distance = 76.2
# width of face in the real world or Object Plane
# centimeter
Known_width = 14.3
# Colors
GREEN = (0, 255, 0)
RED = (0, 0, 255)
WHITE = (255, 255, 255)
BLACK = (0, 0, 0)
# defining the fonts
fonts = cv2.FONT_HERSHEY_COMPLEX
# face detector object
face_detector = cv2.CascadeClassifier("haarcascade_frontalface_default.xml")
# focal length finder function
def Focal_Length_Finder(measured_distance, real_width, width_in_rf_image):
# finding the focal length
focal_length = (width_in_rf_image * measured_distance) / real_width
return focal_length
# distance estimation function
def Distance_finder(Focal_Length, real_face_width, face_width_in_frame):
distance = (real_face_width * Focal_Length) / face_width_in_frame
# return the distance
return distance
def microFacialExpressions(recognizer, width, height):
font = cv2.FONT_HERSHEY_COMPLEX_SMALL
detectorFace = cv2.CascadeClassifier("haarcascade_frontalface_default.xml")
camera = cv2.VideoCapture(0)
recognizer = cv2.face.EigenFaceRecognizer_create()
recognizer.read("classifierEigen.yml")
width, height = 220, 220
while(True):
connected, image = camera.read()
# Grayscale conversion
grayimage = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
facesDetected = detectorFace.detectMultiScale(GrayImage,scaleFactor=1.5, minSize=(100, 100))
for (x, y, l, a) in facesDetected:
faceimage = cv2.resize(greyimage[y:y + a, x:x + l], (width, height))
cv2.rectangle(image, (x, y), (x + l, y + a), (0,0,255), 2)
global id, confidence = recognizer.predict(faceimage)
#If ID is equal to 1, issue the message "Safe to exit" if not, issue the message "Hostile area"
if id == 1:
warning="Safe to exit"
else:
warning = "Hostile area"
cv2.putText(image, warning, (x,y +(a+30)), font, 2, (0,0,255))
return warning
def face_data(image):
face_width = 0 # making face width to zero
# converting color image to gray scale image
gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# detecting face in the image
faces = face_detector.detectMultiScale(gray_image, 1.3, 5)
# looping through the faces detect in the image
# getting coordinates x, y , width and height
for (x, y, h, w) in faces:
# draw the rectangle on the face
cv2.rectangle(image, (x, y), (x + w, y + h), GREEN, 2)
# getting face width in the pixels
face_width = w
# return the face width in pixel
return face_width
# reading reference_image from directory
ref_image = cv2.imread("Ref_image.jpg")
# find the face width(pixels) in the reference_image
ref_image_face_width = face_data(ref_image)
# get the focal by calling "Focal_Length_Finder"
# face width in reference(pixels),
# Known_distance(centimeters),
# known_width(centimeters)
Focal_length_found = Focal_Length_Finder(
Known_distance, Known_width, ref_image_face_width)
print(Focal_length_found)
# show the reference image
cv2.imshow("ref_image", ref_image)
# initialize the camera object so that we
# can get frame from it
cap = cv2.VideoCapture(0, cv2.CAP_DSHOW)
# looping through frame, incoming from
# camera/video
while True:
# reading the frame from camera
_, frame = cap.read()
# calling face_data function to find
# the width of face(pixels) in the frame
face_width_in_frame = face_data(frame)
# check if the face is zero then not
# find the distance
if face_width_in_frame != 0:
# finding the distance by calling function
# Distance finder function need
# these arguments the Focal_Length,
# known_width(centimeters),
# and Known_distance(centimeters)
Distance = Distance_finder(
Focal_length_found, Known_width, face_width_in_frame)
if Distance <= 50 and id:
print("Level S Alert!")
# draw line as background of text
cv2.line(frame, (30, 30), (230, 30), RED, 32)
cv2.line(frame, (30, 30), (230, 30), BLACK, 28)
# Drawing Text on the screen
cv2.putText(
frame, f"Distance: {round(Distance, 2)} CM", (30, 35),
fonts, 0.6, GREEN, 2)
# show the frame on the screen
cv2.imshow("frame", frame)
# quit the program if you press 'q' on keyboard
if cv2.waitKey(1) == ord("q"):
break
# closing the camera
cap.release()
# closing the windows that are opened
cv2.destroyAllWindows()
The global statement does not support assigning to a name, only declaring the name to be a global variable, rather than local variable. While global statements are legal pretty much anywhere, it is strongly recommended to put such declarations at the top of the function.
def microFacialExpressions(recognizer, width, height):
global id, confidence
font = cv2.FONT_HERSHEY_COMPLEX_SMALL
detectorFace = cv2.CascadeClassifier("haarcascade_frontalface_default.xml")
camera = cv2.VideoCapture(0)
recognizer = cv2.face.EigenFaceRecognizer_create()
recognizer.read("classifierEigen.yml")
width, height = 220, 220
while(True):
connected, image = camera.read()
# Grayscale conversion
grayimage = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
facesDetected = detectorFace.detectMultiScale(GrayImage,scaleFactor=1.5, minSize=(100, 100))
for (x, y, l, a) in facesDetected:
faceimage = cv2.resize(greyimage[y:y + a, x:x + l], (width, height))
cv2.rectangle(image, (x, y), (x + l, y + a), (0,0,255), 2)
confidence = recognizer.predict(faceimage)
#If ID is equal to 1, issue the message "Safe to exit" if not, issue the message "Hostile area"
if id == 1:
warning="Safe to exit"
else:
warning = "Hostile area"
cv2.putText(image, warning, (x,y +(a+30)), font, 2, (0,0,255))
return warning
Given that both variables are repeatedly changed in the loop, it's not clear why the last value of either is special enough to need in the global scope. I suspect neither variable needs to be declared global at all.
I am trying to crop an avatar and place it in a given location in another image using python pil.
Here is the output of what I have so far:
And here is the code:
from PIL import Image
from PIL import ImageFont
from PIL import ImageDraw
import textwrap
text = "Creating Twitter Cards dynamically with Python"
background_image = "data/obi-pvc.png" # this is the background
avatar = Image.open("data/avatar.png")
font = "data/fonts/AllertaStencil-Regular.ttf"
background = Image.open(background_image)
background_width, background_height = background.size
avatar.convert('RGBA')
## DO NOT change below this line!!
save_name = f"{text.lower().replace(' ', '_')}.png"
#textwrapped = textwrap.wrap(text, width=text_wrap_width)
# crop avatar
width, height = avatar.size
x = (width - height)//2
avatar_cropped = avatar.crop((x, 0, x+height, height))
width_cr, height_cr = avatar_cropped.size
# create grayscale image with white circle (255) on black background (0)
mask = Image.new('L', avatar_cropped.size)
mask_draw = ImageDraw.Draw(mask)
width, height = avatar_cropped.size
mask_draw.ellipse((0, 0, width, height), fill=255)
# add mask as alpha channel
avatar_cropped.putalpha(mask)
draw = ImageDraw.Draw(background)
font = ImageFont.truetype(font, font_size)
draw.text((offset,margin), '\n'.join(textwrapped), font=font, fill=color)
x, y = avatar_cropped.size
margin = 40
# left top
position_tl = (0 + margin, 0 + margin)
position_tr = (x - margin - width_cr, 0 + margin)
position_bl = (0 + margin, y - margin - height_cr)
position_br = (x - margin - width_cr, y - margin - height_cr)
background.paste(avatar_cropped, position)
background.save(f"data/output/{save_name}")
display(background)
The avatar should fit within the circle. I can't seem to really figure out how to apply the positioning. Thanks
Here is the avatar:
I have this issue, where whatever watermark I put, the background, which is transparent, appears as non-transparent.
Here is the code:
from PIL import Image
import glob
def watermark_with_transparency(input_image_path, output_image_path, watermark_image_path):
base_image = Image.open(input_image_path) # open base image
watermark = Image.open(watermark_image_path) # open water mark
width, height = base_image.size # getting size of image
width_of_watermark, height_of_watermark = watermark.size
position = [width / 2 - width_of_watermark / 2, height / 2 - height_of_watermark / 2]
position[0] = int(position[0])
position[1] = int(position[1])
water = watermark.copy()
water.convert('RGBA')
water.putalpha(70)
water.save('solid.png')
transparent = Image.new('RGBA', (width, height), (0, 0, 0, 0))
transparent.paste(base_image, (0, 0))
transparent.paste(water, position, mask=water)
transparent.show()
transparent.convert('RGB').save(output_image_path)
print('Image Done..!')
for inputImage in glob.glob('images/*.jpg'):
output = inputImage.replace('images\\', '')
outputImage = 'watermark images\\' + str(output)
watermark_with_transparency(inputImage, outputImage, 'watermark images/watermark.png')
Here you may see what the result is:
I am creating a program that converts an Image(from UI) to MNIST array and then predict that digit.
There is nothing wrong in model , I hope, as its predictions are most of the times accurate when testing MNIST image that was provided from data set. But the prediction is poor when I use my image and convert it to MNIST array
def imageprepare(argv):
im = PIL.Image.open(argv).convert('L')
width = float(im.size[0])
height = float(im.size[1])
newImage = PIL.Image.new('L', (28, 28), (255)) # creates white canvas of 28x28 pixels#28 28
if width > height: # check which dimension is bigger
# Width is bigger. Width becomes 20 pixels.
nheight = int(round((20.0 / width * height), 0)) # resize height according to ratio width
if (nheight == 0): # rare case but minimum is 1 pixel
nheight = 1
# resize and sharpen
img = im.resize((20, nheight), PIL.Image.ANTIALIAS).filter(ImageFilter.SHARPEN)
wtop = int(round(((28 - nheight) / 2), 0)) # calculate horizontal position
newImage.paste(img, (4, wtop)) # paste resized image on white canvas
else:
# Height is bigger. Heigth becomes 20 pixels.
nwidth = int(round((20.0 / height * width), 0)) # resize width according to ratio height
if (nwidth == 0): # rare case but minimum is 1 pixel
nwidth = 1
# resize and sharpen
img = im.resize((nwidth, 20), PIL.Image.ANTIALIAS).filter(ImageFilter.SHARPEN)
wleft = int(round(((28 - nwidth) / 2), 0)) # caculate vertical pozition
newImage.paste(img, (wleft, 4)) # paste resized image on white canvas
tv = list(newImage.getdata()) # get pixel values
# normalize pixels to 0 and 1. 0 is pure white, 1 is pure black.
tva = [(255 - x) * 1.0 / 255.0 for x in tv]
return tva
and here is the code that I have used for user interface (mouse as paint brush to enter a digit)(convertToPNG() is used for tranparent background)
def paint(event):
x1, y1 = (event.x - 1), (event.y - 1)
x2, y2 = (event.x + 1), (event.y + 1)
cv.create_oval(x1, y1, x2, y2, fill="black",width=15)
draw.line([x1, y1, x2, y2],fill="black",width=15)
def convertToPNG():
img = PIL.Image.open('./image.png')
img = img.convert("RGBA")
datas = img.getdata()
newData = []
for item in datas:
if item[0] == 255 and item[1] == 255 and item[2] == 255:
newData.append((255, 255, 255, 0))
else:
newData.append(item)
img.putdata(newData)
img.save("./image.png", "PNG")
root = Tk()
cv = Canvas(root, width=width, height=height, bg='white')
cv.pack()
image1 = PIL.Image.new("RGB", (width, height), white)
draw = ImageDraw.Draw(image1)
cv.pack(expand=YES, fill=BOTH)
cv.bind("<B1-Motion>", paint)
button=Button(text="SaveImage",command=save)
button.pack()
button2=Button(text="StartLearning",command=startLearning)
button2.pack()
root.mainloop()