Apologies in advance as i am newbie to OpenCV-Python. I set myself a task to create a Passport type image from the video capture.
Using a head and shoulders Haar Cascade i was able to create a portrait photo but i now want to turn the background to a white background (leaving the head and shoulders portrait in the foreground).
Just not sure how/ best way to do this. Any help would be welcome.
Many thanks in advance.
Here is the code:
import numpy as np
import cv2
# face file
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
# eye file
eye_cascade = cv2.CascadeClassifier('haarcascade_eye.xml')
# head shoulders file
hs_cascade = cv2.CascadeClassifier('HS.xml')
cap = cv2.VideoCapture(1)
while 1:
ret, img = cap.read()
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
headshoulders = hs_cascade.detectMultiScale(gray, 1.3, 3)
# find the head and shoulders
for (x,y,w,h) in headshoulders:
# variable change to make portrait orientation
x = int(x*1.5)
w = int(w/1.5)
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
# crop the image
crop_img = img[y: y + h, x: x + w]
# show original and crop
cv2.imshow('crop', crop_img)
cv2.imshow('img', img)
k = cv2.waitKey(30) & 0xff
if k == 27:
break
elif k == ord('s'):
# save out the portrait image
cv2.imwrite('cropimage.png',crop_img)
# release the camera
cap.release()
cv2.destroyAllWindows()
I got it to work. Here is my solution.
PLEASE NOTE: This worked for HI-RES images (Nikon D7100 - JPEG). LOW-RES did NOT work when i tried a Webcam (Logitech C615).
I used some of the code from a link that was suggested.
# import numpy
import numpy as np
# import cv2
import cv2
# import Matplitlib
from matplotlib import pyplot as plt
# Fill any holes function
def get_holes(image, thresh):
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
im_bw = cv2.threshold(gray, thresh, 255, cv2.THRESH_BINARY)[1]
im_bw_inv = cv2.bitwise_not(im_bw)
im_bw_inv, contour, _ = cv2.findContours(im_bw_inv, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
for cnt in contour:
cv2.drawContours(im_bw_inv, [cnt], 0, 255, -1)
nt = cv2.bitwise_not(im_bw)
im_bw_inv = cv2.bitwise_or(im_bw_inv, nt)
return im_bw_inv
# Remove background Function
def remove_background(image, thresh, scale_factor=.25, kernel_range=range(1, 15), border=None):
border = border or kernel_range[-1]
holes = get_holes(image, thresh)
small = cv2.resize(holes, None, fx=scale_factor, fy=scale_factor)
bordered = cv2.copyMakeBorder(small, border, border, border, border, cv2.BORDER_CONSTANT)
for i in kernel_range:
#kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2*i+1, 2*i+1))
kernel = cv2.getStructuringElement(cv2.MORPH_CROSS, (2*i+1, 2*i+1))
bordered = cv2.morphologyEx(bordered, cv2.MORPH_CLOSE, kernel)
unbordered = bordered[border: -border, border: -border]
mask = cv2.resize(unbordered, (image.shape[1], image.shape[0]))
fg = cv2.bitwise_and(image, image, mask=mask)
return fg
# Load a color image in grayscale
img = cv2.imread('original/11.png')
# Start background removal -- Parameters are <image> and <threshold level>
nb_img = remove_background(img, 180)
# Change Black Pixels to WHITE
nb_img[np.where((nb_img==[0,0,0]).all(axis=2))] = [255,255,255]
# resize the viewing size (as the images are too big for the screen
small = cv2.resize(nb_img, (300, 400))
# Show the finished image
cv2.imshow('image',small)
k = cv2.waitKey(0) & 0xFF
if k == 27: #wait for ESC key to exit
# if ESC pressed close the camera windows
cv2.destroyAllWindows()
elif k == ord('s'): #wait for 's' key to save and exit
# Save the img(greyscale version)
cv2.imwrite('bg_removal/11.png',small)
cv2.destroyAllWindows()
Related
How can I overlay a transparent PNG onto another image without losing it's transparency using openCV in python?
import cv2
background = cv2.imread('field.jpg')
overlay = cv2.imread('dice.png')
# Help please
cv2.imwrite('combined.png', background)
Desired output:
Sources:
Background Image
Overlay
import cv2
background = cv2.imread('field.jpg')
overlay = cv2.imread('dice.png')
added_image = cv2.addWeighted(background,0.4,overlay,0.1,0)
cv2.imwrite('combined.png', added_image)
The correct answer to this was far too hard to come by, so I'm posting this answer even though the question is really old. What you are looking for is "over" compositing, and the algorithm for this can be found on Wikipedia: https://en.wikipedia.org/wiki/Alpha_compositing
I am far from an expert with OpenCV, but after some experimentation this is the most efficient way I have found to accomplish the task:
import cv2
background = cv2.imread("background.png", cv2.IMREAD_UNCHANGED)
foreground = cv2.imread("overlay.png", cv2.IMREAD_UNCHANGED)
# normalize alpha channels from 0-255 to 0-1
alpha_background = background[:,:,3] / 255.0
alpha_foreground = foreground[:,:,3] / 255.0
# set adjusted colors
for color in range(0, 3):
background[:,:,color] = alpha_foreground * foreground[:,:,color] + \
alpha_background * background[:,:,color] * (1 - alpha_foreground)
# set adjusted alpha and denormalize back to 0-255
background[:,:,3] = (1 - (1 - alpha_foreground) * (1 - alpha_background)) * 255
# display the image
cv2.imshow("Composited image", background)
cv2.waitKey(0)
The following code will use the alpha channels of the overlay image to correctly blend it into the background image, use x and y to set the top-left corner of the overlay image.
import cv2
import numpy as np
def overlay_transparent(background, overlay, x, y):
background_width = background.shape[1]
background_height = background.shape[0]
if x >= background_width or y >= background_height:
return background
h, w = overlay.shape[0], overlay.shape[1]
if x + w > background_width:
w = background_width - x
overlay = overlay[:, :w]
if y + h > background_height:
h = background_height - y
overlay = overlay[:h]
if overlay.shape[2] < 4:
overlay = np.concatenate(
[
overlay,
np.ones((overlay.shape[0], overlay.shape[1], 1), dtype = overlay.dtype) * 255
],
axis = 2,
)
overlay_image = overlay[..., :3]
mask = overlay[..., 3:] / 255.0
background[y:y+h, x:x+w] = (1.0 - mask) * background[y:y+h, x:x+w] + mask * overlay_image
return background
This code will mutate background so create a copy if you wish to preserve the original background image.
Been a while since this question appeared, but I believe this is the right simple answer, which could still help somebody.
background = cv2.imread('road.jpg')
overlay = cv2.imread('traffic sign.png')
rows,cols,channels = overlay.shape
overlay=cv2.addWeighted(background[250:250+rows, 0:0+cols],0.5,overlay,0.5,0)
background[250:250+rows, 0:0+cols ] = overlay
This will overlay the image over the background image such as shown here:
Ignore the ROI rectangles
Note that I used a background image of size 400x300 and the overlay image of size 32x32, is shown in the x[0-32] and y[250-282] part of the background image according to the coordinates I set for it, to first calculate the blend and then put the calculated blend in the part of the image where I want to have it.
(overlay is loaded from disk, not from the background image itself,unfortunately the overlay image has its own white background, so you can see that too in the result)
If performance isn't a concern then you can iterate over each pixel of the overlay and apply it to the background. This isn't very efficient, but it does help to understand how to work with png's alpha layer.
slow version
import cv2
background = cv2.imread('field.jpg')
overlay = cv2.imread('dice.png', cv2.IMREAD_UNCHANGED) # IMREAD_UNCHANGED => open image with the alpha channel
height, width = overlay.shape[:2]
for y in range(height):
for x in range(width):
overlay_color = overlay[y, x, :3] # first three elements are color (RGB)
overlay_alpha = overlay[y, x, 3] / 255 # 4th element is the alpha channel, convert from 0-255 to 0.0-1.0
# get the color from the background image
background_color = background[y, x]
# combine the background color and the overlay color weighted by alpha
composite_color = background_color * (1 - overlay_alpha) + overlay_color * overlay_alpha
# update the background image in place
background[y, x] = composite_color
cv2.imwrite('combined.png', background)
result:
fast version
I stumbled across this question while trying to add a png overlay to a live video feed. The above solution is way too slow for that. We can make the algorithm significantly faster by using numpy's vector functions.
note: This was my first real foray into numpy so there may be better/faster methods than what I've come up with.
import cv2
import numpy as np
background = cv2.imread('field.jpg')
overlay = cv2.imread('dice.png', cv2.IMREAD_UNCHANGED) # IMREAD_UNCHANGED => open image with the alpha channel
# separate the alpha channel from the color channels
alpha_channel = overlay[:, :, 3] / 255 # convert from 0-255 to 0.0-1.0
overlay_colors = overlay[:, :, :3]
# To take advantage of the speed of numpy and apply transformations to the entire image with a single operation
# the arrays need to be the same shape. However, the shapes currently looks like this:
# - overlay_colors shape:(width, height, 3) 3 color values for each pixel, (red, green, blue)
# - alpha_channel shape:(width, height, 1) 1 single alpha value for each pixel
# We will construct an alpha_mask that has the same shape as the overlay_colors by duplicate the alpha channel
# for each color so there is a 1:1 alpha channel for each color channel
alpha_mask = np.dstack((alpha_channel, alpha_channel, alpha_channel))
# The background image is larger than the overlay so we'll take a subsection of the background that matches the
# dimensions of the overlay.
# NOTE: For simplicity, the overlay is applied to the top-left corner of the background(0,0). An x and y offset
# could be used to place the overlay at any position on the background.
h, w = overlay.shape[:2]
background_subsection = background[0:h, 0:w]
# combine the background with the overlay image weighted by alpha
composite = background_subsection * (1 - alpha_mask) + overlay_colors * alpha_mask
# overwrite the section of the background image that has been updated
background[0:h, 0:w] = composite
cv2.imwrite('combined.png', background)
How much faster? On my machine the slow method takes ~3 seconds and the optimized method takes ~ 30 ms. So about
100 times faster!
Wrapped up in a function
This function handles foreground and background images of different sizes and also supports negative and positive offsets the move the overlay across the bounds of the background image in any direction.
import cv2
import numpy as np
def add_transparent_image(background, foreground, x_offset=None, y_offset=None):
bg_h, bg_w, bg_channels = background.shape
fg_h, fg_w, fg_channels = foreground.shape
assert bg_channels == 3, f'background image should have exactly 3 channels (RGB). found:{bg_channels}'
assert fg_channels == 4, f'foreground image should have exactly 4 channels (RGBA). found:{fg_channels}'
# center by default
if x_offset is None: x_offset = (bg_w - fg_w) // 2
if y_offset is None: y_offset = (bg_h - fg_h) // 2
w = min(fg_w, bg_w, fg_w + x_offset, bg_w - x_offset)
h = min(fg_h, bg_h, fg_h + y_offset, bg_h - y_offset)
if w < 1 or h < 1: return
# clip foreground and background images to the overlapping regions
bg_x = max(0, x_offset)
bg_y = max(0, y_offset)
fg_x = max(0, x_offset * -1)
fg_y = max(0, y_offset * -1)
foreground = foreground[fg_y:fg_y + h, fg_x:fg_x + w]
background_subsection = background[bg_y:bg_y + h, bg_x:bg_x + w]
# separate alpha and color channels from the foreground image
foreground_colors = foreground[:, :, :3]
alpha_channel = foreground[:, :, 3] / 255 # 0-255 => 0.0-1.0
# construct an alpha_mask that matches the image shape
alpha_mask = np.dstack((alpha_channel, alpha_channel, alpha_channel))
# combine the background with the overlay image weighted by alpha
composite = background_subsection * (1 - alpha_mask) + foreground_colors * alpha_mask
# overwrite the section of the background image that has been updated
background[bg_y:bg_y + h, bg_x:bg_x + w] = composite
example usage:
background = cv2.imread('field.jpg')
overlay = cv2.imread('dice.png', cv2.IMREAD_UNCHANGED) # IMREAD_UNCHANGED => open image with the alpha channel
x_offset = 0
y_offset = 0
print("arrow keys to move the dice. ESC to quit")
while True:
img = background.copy()
add_transparent_image(img, overlay, x_offset, y_offset)
cv2.imshow("", img)
key = cv2.waitKey()
if key == 0: y_offset -= 10 # up
if key == 1: y_offset += 10 # down
if key == 2: x_offset -= 10 # left
if key == 3: x_offset += 10 # right
if key == 27: break # escape
You need to open the transparent png image using the flag IMREAD_UNCHANGED
Mat overlay = cv::imread("dice.png", IMREAD_UNCHANGED);
Then split the channels, group the RGB and use the transparent channel as an mask, do like that:
/**
* #brief Draws a transparent image over a frame Mat.
*
* #param frame the frame where the transparent image will be drawn
* #param transp the Mat image with transparency, read from a PNG image, with the IMREAD_UNCHANGED flag
* #param xPos x position of the frame image where the image will start.
* #param yPos y position of the frame image where the image will start.
*/
void drawTransparency(Mat frame, Mat transp, int xPos, int yPos) {
Mat mask;
vector<Mat> layers;
split(transp, layers); // seperate channels
Mat rgb[3] = { layers[0],layers[1],layers[2] };
mask = layers[3]; // png's alpha channel used as mask
merge(rgb, 3, transp); // put together the RGB channels, now transp insn't transparent
transp.copyTo(frame.rowRange(yPos, yPos + transp.rows).colRange(xPos, xPos + transp.cols), mask);
}
Can be called like that:
drawTransparency(background, overlay, 10, 10);
To overlay png image watermark over normal 3 channel jpeg image
import cv2
import numpy as np
def logoOverlay(image,logo,alpha=1.0,x=0, y=0, scale=1.0):
(h, w) = image.shape[:2]
image = np.dstack([image, np.ones((h, w), dtype="uint8") * 255])
overlay = cv2.resize(logo, None,fx=scale,fy=scale)
(wH, wW) = overlay.shape[:2]
output = image.copy()
# blend the two images together using transparent overlays
try:
if x<0 : x = w+x
if y<0 : y = h+y
if x+wW > w: wW = w-x
if y+wH > h: wH = h-y
print(x,y,wW,wH)
overlay=cv2.addWeighted(output[y:y+wH, x:x+wW],alpha,overlay[:wH,:wW],1.0,0)
output[y:y+wH, x:x+wW ] = overlay
except Exception as e:
print("Error: Logo position is overshooting image!")
print(e)
output= output[:,:,:3]
return output
Usage:
background = cv2.imread('image.jpeg')
overlay = cv2.imread('logo.png', cv2.IMREAD_UNCHANGED)
print(overlay.shape) # must be (x,y,4)
print(background.shape) # must be (x,y,3)
# downscale logo by half and position on bottom right reference
out = logoOverlay(background,overlay,scale=0.5,y=-100,x=-100)
cv2.imshow("test",out)
cv2.waitKey(0)
import cv2
import numpy as np
background = cv2.imread('background.jpg')
overlay = cv2.imread('cloudy.png')
overlay = cv2.resize(overlay, (200,200))
# overlay = for_transparent_removal(overlay)
h, w = overlay.shape[:2]
shapes = np.zeros_like(background, np.uint8)
shapes[0:h, 0:w] = overlay
alpha = 0.8
mask = shapes.astype(bool)
# option first
background[mask] = cv2.addWeighted(shapes, alpha, shapes, 1 - alpha, 0)[mask]
cv2.imwrite('combined.png', background)
# option second
background[mask] = cv2.addWeighted(background, alpha, overlay, 1 - alpha, 0)[mask]
# NOTE : above both option will give you image overlays but effect would be changed
cv2.imwrite('combined.1.png', background)
**Use this function to place your overlay on any background image.
if want to resize overlay use this overlay = cv2.resize(overlay, (200,200)) and then pass resized overlay into the function.
**
import cv2
import numpy as np
def image_overlay_second_method(img1, img2, location, min_thresh=0, is_transparent=False):
h, w = img1.shape[:2]
h1, w1 = img2.shape[:2]
x, y = location
roi = img1[y:y + h1, x:x + w1]
gray = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)
_, mask = cv2.threshold(gray, min_thresh, 255, cv2.THRESH_BINARY)
mask_inv = cv2.bitwise_not(mask)
img_bg = cv2.bitwise_and(roi, roi, mask=mask_inv)
img_fg = cv2.bitwise_and(img2, img2, mask=mask)
dst = cv2.add(img_bg, img_fg)
if is_transparent:
dst = cv2.addWeighted(img1[y:y + h1, x:x + w1], 0.1, dst, 0.9, None)
img1[y:y + h1, x:x + w1] = dst
return img1
if __name__ == '__main__':
background = cv2.imread('background.jpg')
overlay = cv2.imread('overlay.png')
output = image_overlay_third_method(background, overlay, location=(800,50), min_thresh=0, is_transparent=True)
cv2.imwrite('output.png', output)
background.jpg
output.png
I want to find the HSV value of a LASER dot using opencv and python. I got the code http://opencv-srf.blogspot.com.au/2010/09/object-detection-using-color-seperation.html from here but it is in c++, installing visual studio and opencv takes time so i changed the code in python
import cv2
import numpy as np
def callback(x):
pass
cap = cv2.VideoCapture(0)
cv2.namedWindow('image')
ilowH = 0
ihighH = 179
ilowS = 0
ihighS = 255
ilowV = 0
ihighV = 255
# create trackbars for color change
cv2.createTrackbar('lowH','image',ilowH,179,callback)
cv2.createTrackbar('highH','image',ihighH,179,callback)
cv2.createTrackbar('lowS','image',ilowS,255,callback)
cv2.createTrackbar('highS','image',ihighS,255,callback)
cv2.createTrackbar('lowV','image',ilowV,255,callback)
cv2.createTrackbar('highV','image',ihighV,255,callback)
while(1):
ret, frame = cap.read()
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
cv2.imshow('hsv', hsv)
lower_hsv = np.array([ilowH, ilowS, ilowV])
higher_hsv = np.array([ihighH, ihighS, ihighV])
mask = cv2.inRange(hsv, lower_hsv, higher_hsv)
cv2.imshow('mask', mask)
cv2.imshow('frame', frame)
print ilowH, ilowS, ilowV
if(cv2.waitKey(1) & 0xFF == ord('q')):
break
cv2.destroyAllWindows()
cap.release()
but this code doesnot threshold anything. It seems like the trackbars i created doesnot change the value of ilowH ,ilowS, ilowV . I checked it by printing those values inside while loop. What could be the problem for not thresholding any of those values or is there better code in python to find HSV values of the LASER.
Thank you, any help is appreciated.
You can grab the trackbar values with cv2.getTrackbarPos(). Also note that sometimes it puts trackbars out of order, which is annoying, but at least they're labeled.
However, I don't think that these trackbars will work very well for live video feed. There's a lot of freezing issues. You'll have to have a super low framerate (works for me with cv2.waitKey(500) if you're actually trying to display it). This is mostly due to the trackbars sucking, not the thresholding operation, which is not that slow.
You need to add your trackbars after you create the named window. Then, for your while loop, try:
while True:
# grab the frame
ret, frame = cap.read()
# get trackbar positions
ilowH = cv2.getTrackbarPos('lowH', 'image')
ihighH = cv2.getTrackbarPos('highH', 'image')
ilowS = cv2.getTrackbarPos('lowS', 'image')
ihighS = cv2.getTrackbarPos('highS', 'image')
ilowV = cv2.getTrackbarPos('lowV', 'image')
ihighV = cv2.getTrackbarPos('highV', 'image')
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
lower_hsv = np.array([ilowH, ilowS, ilowV])
higher_hsv = np.array([ihighH, ihighS, ihighV])
mask = cv2.inRange(hsv, lower_hsv, higher_hsv)
frame = cv2.bitwise_and(frame, frame, mask=mask)
# show thresholded image
cv2.imshow('image', frame)
k = cv2.waitKey(1000) & 0xFF # large wait time to remove freezing
if k == 113 or k == 27:
break
and finally end the file with a cv2.destroyAllWindows()
As an aside, the maximum H value for HSV is 180, not 179.
Shameless plug: I happened to just finish a project doing precisely this, but on images. You can grab it on GitHub here. There is an example; try running it and then modifying as you need. It will let you change the colorspace and threshold inside each different colorspace, and it will print the final thresholding values that you ended on. Additionally it will return the output image from the operation for you to use, too. Hopefully it is useful for you! Feel free to send any issues or suggestions through GitHub for the project.
Here is an example of it running:
And as output it gives you:
Colorspace: HSV
Lower bound: [68.4, 0.0, 0.0]
Upper bound: [180.0, 255.0, 255.0]
as well as the binary image. I am currently working on getting this into a web application as well, but that probably won't be finished for a few days.
Use this code to find range of masking of real-time video! this might save you time. Below is a whole code, Check it and run it to have a test.
import cv2
import numpy as np
camera = cv2.VideoCapture(0)
def nothing(x):
pass
cv2.namedWindow('marking')
cv2.createTrackbar('H Lower','marking',0,179,nothing)
cv2.createTrackbar('H Higher','marking',179,179,nothing)
cv2.createTrackbar('S Lower','marking',0,255,nothing)
cv2.createTrackbar('S Higher','marking',255,255,nothing)
cv2.createTrackbar('V Lower','marking',0,255,nothing)
cv2.createTrackbar('V Higher','marking',255,255,nothing)
while(1):
_,img = camera.read()
img = cv2.flip(img,1)
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
hL = cv2.getTrackbarPos('H Lower','marking')
hH = cv2.getTrackbarPos('H Higher','marking')
sL = cv2.getTrackbarPos('S Lower','marking')
sH = cv2.getTrackbarPos('S Higher','marking')
vL = cv2.getTrackbarPos('V Lower','marking')
vH = cv2.getTrackbarPos('V Higher','marking')
LowerRegion = np.array([hL,sL,vL],np.uint8)
upperRegion = np.array([hH,sH,vH],np.uint8)
redObject = cv2.inRange(hsv,LowerRegion,upperRegion)
kernal = np.ones((1,1),"uint8")
red = cv2.morphologyEx(redObject,cv2.MORPH_OPEN,kernal)
red = cv2.dilate(red,kernal,iterations=1)
res1=cv2.bitwise_and(img, img, mask = red)
cv2.imshow("Masking ",res1)
if cv2.waitKey(10) & 0xFF == ord('q'):
camera.release()
cv2.destroyAllWindows()
break`
Thanks!
Hugs..
I want to extract only the rectangular part of the mouth detected by my code how can I do it:
import numpy as np
import cv2
face_cascade = cv2.CascadeClassifier('/usr/local/share/OpenCV/haarcascades/haarcascade_frontalface_default.xml')
mouth_cascade = cv2.CascadeClassifier('/usr/local/share/OpenCV/haarcascades/haarcascade_smile.xml')
img = cv2.imread('Images/image_0033.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.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)
roi_gray = gray[y:y+h, x:x+w]
roi_color = img[y:y+h, x:x+w]
mouth = mouth_cascade.detectMultiScale(roi_gray,2.0,25)
for (ex,ey,ew,eh) in mouth:
cv2.rectangle(roi_color,(ex,ey),(ex+ew,ey+eh),(0,255,0),3)
cv2.imshow('img',nwimg)
cv2.waitKey(0)
cv2.destroyAllWindows()
As seen in the code I just want to extract the rectangular mouth region I have used commands like var = img[y:y+h,x:x+w] but this has not worked.
It is simple, replace this line:
cv2.rectangle(roi_color,(ex,ey),(ex+ew,ey+eh),(0,255,0),3) with
cv2.rectangle(img,(ex,ey),(ex+ew,ey+eh),(0,255,0),3)
and display the following:
cv2.imshow('Detected Mouth',img)
In this way you will draw a rectangle over the mouth.
EDIT
You can crop your region of interest (in this case the mouth) using numpy operation as follows:
crop_img = img[ey:ey+eh, ex:ex+ew]
cv2.imshow('Cropped Mouth',crop_img)
This is what I got:
Sample 1:
Sample 2:
I took the code from this post:
how to crop the detected face in opencv and save roi as image in opencv python
The problem is that when I run this code, it shows a grey screen instead of showing the video from webcam.
Here's my coding:
import cv2
import os, sys
TRAINSET = "haarcascade_frontalface_default.xml"
DOWNSCALE = 4
cam = cv2.VideoCapture(0) #capture a video
cv2.namedWindow("preview")
classifier = cv2.CascadeClassifier(TRAINSET)
Compare_images=[]
for file in os.listdir("D:/Python code"):
if file.endswith(".jpg"):
Compare_images.append(file)
while True: # try to get the first frame
_, frame = cam.read()
key = cv2.waitKey(20)
if(key==32):
print "Name of Image:"
n= raw_input()
value=len(Compare_images)
cv2.imwrite('images/image'+str(n)+'.jpg', frame)
saved_image=cv2.imread("images/image"+str(n)+".jpg")
minisize = (saved_image.shape[1]/DOWNSCALE,saved_image.shape[0]/DOWNSCALE)
miniframe = cv2.resize(saved_image, minisize)
faces = classifier.detectMultiScale(miniframe)
for f in faces:
x, y, w, h = [ v*DOWNSCALE for v in f ]
print x
print y,w,h
x0,y0=int(x),int(y)
x1,y1=int(x+w),int(y+h)
print x0,y0,y1,y0
image = cv2.rectangle(saved_image, (x0,y0), (x1,y1), (0,0,255),2)
roi=saved_image[y0:y1,x0:x1]#crop
cv2.imwrite('roi.jpg',roi)
cv2.imshow("adsa", saved_image)
cv2.putText(frame, "Press ESC to close.", (5, 25), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255,255,255))
cv2.imshow("preview", frame)
I'm really new into python, and I would really appreciate it if you are able to help!
Hello I am running the python opencv code below on a raspberry pi 3 and using a usb camera.The program tracks a persons face and overlays a mask image over the face. My program keeps crashing and showing the error below:. Also the image masking the persons face is not removing the background color to just leave the image mask. Hope you can help.
:1036: error : (-215) mask.size == src1.size in function binary_op
import cv2
import numpy as np
face_cascade = cv2.CascadeClassifier('cascade_files/haarcascade_frontalface_alt.xml')
face_mask = cv2.imread('../images/mask_skull.png')
h_mask, w_mask = face_mask.shape[:2]
if face_cascade.empty():
raise IOError('Unable to load the face cascade classifier xml file')
cap = cv2.VideoCapture(0)
scaling_factor = 0.5
while True:
ret, frame = cap.read()
frame = cv2.resize(frame, None, fx=scaling_factor, fy=scaling_factor, interpolation=cv2.INTER_AREA)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
face_rects = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x,y,w,h) in face_rects:
if h > 0 and w > 0:
h, w = int(1.4*h), int(1.0*w)
y -= 0.1*h
frame_roi = frame[y:y+h, x:x+w]
face_mask_small = cv2.resize(face_mask, (w, h), interpolation=cv2.INTER_AREA)
gray_mask = cv2.cvtColor(face_mask_small, cv2.COLOR_BGR2GRAY)
ret, mask = cv2.threshold(gray_mask, 180, 255, cv2.THRESH_BINARY_INV)
mask_inv = cv2.bitwise_not(mask)
masked_face = cv2.bitwise_and(face_mask_small, face_mask_small, mask=mask)
masked_frame = cv2.bitwise_and(frame_roi, frame_roi, mask=mask_inv)
frame[y:y+h, x:x+w] = cv2.add(masked_face, masked_frame)
cv2.imshow('Face Detector', frame)
c = cv2.waitKey(1)
if c == 27:
break
cap.release()
cv2.destroyAllWindows()