overlay a smaller image on a larger image python OpenCv

Hi I am creating a program that replaces a face in a image with someone else's face. However, I am stuck on trying to insert the new face into the original, larger image. I have researched ROI and addWeight(needs the images to be the same size) but I haven't found a way to do this in python. Any advise is great. I am new to opencv.

I am using the following test images:

smaller_image:

larger_image:

Here is my Code so far... a mixer of other samples:

import cv2
import cv2.cv as cv
import sys
import numpy

def detect(img, cascade):
	rects = cascade.detectMultiScale(img, scaleFactor=1.1, minNeighbors=3, minSize=(10, 10), flags = cv.CV_HAAR_SCALE_IMAGE)
	if len(rects) == 0:
		return []
	rects[:,2:] += rects[:,:2]
	return rects

def draw_rects(img, rects, color):
	for x1, y1, x2, y2 in rects:
		cv2.rectangle(img, (x1, y1), (x2, y2), color, 2)

if __name__ == '__main__':
	if len(sys.argv) != 2:                                         ## Check for error in usage syntax

	print "Usage : python faces.py <image_file>"

else:
	img = cv2.imread(sys.argv[1],cv2.CV_LOAD_IMAGE_COLOR)  ## Read image file

	if (img == None):                                     
		print "Could not open or find the image"
	else:
		cascade = cv2.CascadeClassifier("haarcascade_frontalface_alt.xml")
		gray = cv2.cvtColor(img, cv.CV_BGR2GRAY)
		gray = cv2.equalizeHist(gray)

		rects = detect(gray, cascade)

		## Extract face coordinates			
		x1 = rects[0][3]
		y1 = rects[0][0]
		x2 = rects[0][4]
		y2 = rects[0][5]
		y=y2-y1
		x=x2-x1
		## Extract face ROI
		faceROI = gray[x1:x2, y1:y2]

		## Show face ROI
		cv2.imshow('Display face ROI', faceROI)
		small = cv2.imread("average_face.png",cv2.CV_LOAD_IMAGE_COLOR)  
		print "here"
		small=cv2.resize(small, (x, y))
		cv2.namedWindow('Display image')          ## create window for display
		cv2.imshow('Display image', small)          ## Show image in the window

		print "size of image: ", img.shape        ## print size of image
		cv2.waitKey(1000)              

A simple way to achieve what you want:

import cv2
s_img = cv2.imread("smaller_image.png")
l_img = cv2.imread("larger_image.jpg")
x_offset=y_offset=50
l_img[y_offset:y_offset+s_img.shape[0], x_offset:x_offset+s_img.shape[1]] = s_img

Update

I suppose you want to take care of the alpha channel too. Here is a quick and dirty way of doing so:

s_img = cv2.imread("smaller_image.png", -1)

y1, y2 = y_offset, y_offset + s_img.shape[0]
x1, x2 = x_offset, x_offset + s_img.shape[1]

alpha_s = s_img[:, :, 3] / 255.0
alpha_l = 1.0 - alpha_s

for c in range(0, 3):
    l_img[y1:y2, x1:x2, c] = (alpha_s * s_img[:, :, c] +
                              alpha_l * l_img[y1:y2, x1:x2, c])

Using @fireant's idea, I wrote up a function to handle overlays. This works well for any position argument (including negative positions).

def overlay_image_alpha(img, img_overlay, x, y, alpha_mask):
    """Overlay `img_overlay` onto `img` at (x, y) and blend using `alpha_mask`.

    `alpha_mask` must have same HxW as `img_overlay` and values in range [0, 1].
    """
    # Image ranges
    y1, y2 = max(0, y), min(img.shape[0], y + img_overlay.shape[0])
    x1, x2 = max(0, x), min(img.shape[1], x + img_overlay.shape[1])

    # Overlay ranges
    y1o, y2o = max(0, -y), min(img_overlay.shape[0], img.shape[0] - y)
    x1o, x2o = max(0, -x), min(img_overlay.shape[1], img.shape[1] - x)

    # Exit if nothing to do
    if y1 >= y2 or x1 >= x2 or y1o >= y2o or x1o >= x2o:
        return

    # Blend overlay within the determined ranges
    img_crop = img[y1:y2, x1:x2]
    img_overlay_crop = img_overlay[y1o:y2o, x1o:x2o]
    alpha = alpha_mask[y1o:y2o, x1o:x2o, np.newaxis]
    alpha_inv = 1.0 - alpha

    img_crop[:] = alpha * img_overlay_crop + alpha_inv * img_crop

Example usage:

import numpy as np
from PIL import Image

# Prepare inputs
x, y = 50, 0
img = np.array(Image.open("img_large.jpg"))
img_overlay_rgba = np.array(Image.open("img_small.png"))

# Perform blending
alpha_mask = img_overlay_rgba[:, :, 3] / 255.0
img_result = img[:, :, :3].copy()
img_overlay = img_overlay_rgba[:, :, :3]
overlay_image_alpha(img_result, img_overlay, x, y, alpha_mask)

# Save result
Image.fromarray(img_result).save("img_result.jpg")

Result:

If you encounter errors or unusual outputs, please ensure:

• img should not contain an alpha channel. (e.g. If it is RGBA, convert to RGB first.)
• img_overlay has the same number of channels as img.

Based on fireant's excellent answer above, here is the alpha blending but a bit more human legible. You may need to swap 1.0-alpha and alpha depending on which direction you're merging (mine is swapped from fireant's answer).

o* == s_img.* b* == b_img.*

for c in range(0,3):
    alpha = s_img[oy:oy+height, ox:ox+width, 3] / 255.0
    color = s_img[oy:oy+height, ox:ox+width, c] * (1.0-alpha)
    beta  = l_img[by:by+height, bx:bx+width, c] * (alpha)

    l_img[by:by+height, bx:bx+width, c] = color + beta

Here it is:

def put4ChannelImageOn4ChannelImage(back, fore, x, y):
    rows, cols, channels = fore.shape    
    trans_indices = fore[...,3] != 0 # Where not transparent
    overlay_copy = back[y:y+rows, x:x+cols] 
    overlay_copy[trans_indices] = fore[trans_indices]
    back[y:y+rows, x:x+cols] = overlay_copy

#test
background = np.zeros((1000, 1000, 4), np.uint8)
background[:] = (127, 127, 127, 1)
overlay = cv2.imread('imagee.png', cv2.IMREAD_UNCHANGED)
put4ChannelImageOn4ChannelImage(background, overlay, 5, 5)

A simple function that blits an image front onto an image back and returns the result. It works with both 3 and 4-channel images and deals with the alpha channel. Overlaps are handled as well.

The output image has the same size as back, but always 4 channels.
The output alpha channel is given by (u+v)/(1+uv) where u,v are the alpha channels of the front and back image and -1 <= u,v <= 1. Where there is no overlap with front, the alpha value from back is taken.

import cv2

def merge_image(back, front, x,y):
    # convert to rgba
    if back.shape[2] == 3:
        back = cv2.cvtColor(back, cv2.COLOR_BGR2BGRA)
    if front.shape[2] == 3:
        front = cv2.cvtColor(front, cv2.COLOR_BGR2BGRA)

    # crop the overlay from both images
    bh,bw = back.shape[:2]
    fh,fw = front.shape[:2]
    x1, x2 = max(x, 0), min(x+fw, bw)
    y1, y2 = max(y, 0), min(y+fh, bh)
    front_cropped = front[y1-y:y2-y, x1-x:x2-x]
    back_cropped = back[y1:y2, x1:x2]

    alpha_front = front_cropped[:,:,3:4] / 255
    alpha_back = back_cropped[:,:,3:4] / 255
    
    # replace an area in result with overlay
    result = back.copy()
    print(f'af: {alpha_front.shape}\nab: {alpha_back.shape}\nfront_cropped: {front_cropped.shape}\nback_cropped: {back_cropped.shape}')
    result[y1:y2, x1:x2, :3] = alpha_front * front_cropped[:,:,:3] + (1-alpha_front) * back_cropped[:,:,:3]
    result[y1:y2, x1:x2, 3:4] = (alpha_front + alpha_back) / (1 + alpha_front*alpha_back) * 255

    return result

When attempting to write to the destination image using any of these answers above and you get the following error:

ValueError: assignment destination is read-only

A quick potential fix is to set the WRITEABLE flag to true.

img.setflags(write=1)

For just add an alpha channel to s_img I just use cv2.addWeighted before the line l_img[y_offset:y_offset+s_img.shape[0], x_offset:x_offset+s_img.shape[1]] = s_img

as following:
s_img=cv2.addWeighted(l_img[y_offset:y_offset+s_img.shape[0], x_offset:x_offset+s_img.shape[1]],0.5,s_img,0.5,0)

A simple 4on4 pasting function that works-

def paste(background,foreground,pos=(0,0)):
    #get position and crop pasting area if needed
    x = pos[0]
    y = pos[1]
    bgWidth = background.shape[0]
    bgHeight = background.shape[1]
    frWidth = foreground.shape[0]
    frHeight = foreground.shape[1]
    width = bgWidth-x
    height = bgHeight-y
    if frWidth<width:
        width = frWidth
    if frHeight<height:
        height = frHeight
    # normalize alpha channels from 0-255 to 0-1
    alpha_background = background[x:x+width,y:y+height,3] / 255.0
    alpha_foreground = foreground[:width,:height,3] / 255.0
    # set adjusted colors
    for color in range(0, 3):
        fr = alpha_foreground * foreground[:width,:height,color]
        bg = alpha_background * background[x:x+width,y:y+height,color] * (1 - alpha_foreground)
        background[x:x+width,y:y+height,color] = fr+bg
    # set adjusted alpha and denormalize back to 0-255
    background[x:x+width,y:y+height,3] = (1 - (1 - alpha_foreground) * (1 - alpha_background)) * 255
    return background

I reworked @fireant's concept to allow for optional alpha masks and allow any x or y, including values outside of the bounds of the image. It will crop to the bounds.

def overlay_image_alpha(img, img_overlay, x, y, alpha_mask=None):
    """Overlay `img_overlay` onto `img` at (x, y) and blend using optional `alpha_mask`.

    `alpha_mask` must have same HxW as `img_overlay` and values in range [0, 1].
    """

    if y < 0 or y + img_overlay.shape[0] > img.shape[0] or x < 0 or x + img_overlay.shape[1] > img.shape[1]:
        y_origin = 0 if y > 0 else -y
        y_end = img_overlay.shape[0] if y < 0 else min(img.shape[0] - y, img_overlay.shape[0])

        x_origin = 0 if x > 0 else -x
        x_end = img_overlay.shape[1] if x < 0 else min(img.shape[1] - x, img_overlay.shape[1])

        img_overlay_crop = img_overlay[y_origin:y_end, x_origin:x_end]
        alpha = alpha_mask[y_origin:y_end, x_origin:x_end] if alpha_mask is not None else None
    else:
        img_overlay_crop = img_overlay
        alpha = alpha_mask

    y1 = max(y, 0)
    y2 = min(img.shape[0], y1 + img_overlay_crop.shape[0])

    x1 = max(x, 0)
    x2 = min(img.shape[1], x1 + img_overlay_crop.shape[1])

    img_crop = img[y1:y2, x1:x2]
    img_crop[:] = alpha * img_overlay_crop + (1.0 - alpha) * img_crop if alpha is not None else img_overlay_crop