如果我理解正确，您想在新图像中突出显示输入图像和输出图像之间的差异。为此，您可以采用定量方法，使用Image Quality Assessment: From Error Visibility to Structural Similarity中引入的结构相似性指数（SSIM）来确定图像之间的确切差异。该方法已经在scikit-image库中实现了图像处理。您可以将scikit-image与pip install scikit-image一起安装。

skimage.measure.compare_ssim()函数返回一个score和一个diff图像。 score代表两个输入图像之间的结构相似性指标，并且可以落在[-1,1]范围内，其值更接近一个代表更高相似性的值。但是，由于您只对两个图像的不同之处感兴趣，因此我们将重点关注diff图像。具体地，diff图像包含实际图像差异，其中较暗的区域具有更大的视差。较大的差异区域以黑色突出显示，而较小的差异以灰色突出显示。这是diff图片

如果您仔细观察，可能会由于.jpg有损压缩而出现灰色噪点区域。因此，为了获得更清晰的结果，我们执行形态学运算以平滑图像。如果图像使用无损图像压缩格式（例如.png），我们将获得更清晰的结果。整理完图像后，我们突出显示绿色的差异

from skimage.measure import compare_ssim
import numpy as np
import cv2

# Load images and convert to grayscale
image1 = cv2.imread('1.jpg')
image2 = cv2.imread('2.jpg')
image1_gray = cv2.cvtColor(image1,cv2.COLOR_BGR2GRAY)
image2_gray = cv2.cvtColor(image2,cv2.COLOR_BGR2GRAY)

# Compute SSIM between two images
(score,diff) = compare_ssim(image1_gray,image2_gray,full=True)

# The diff image contains the actual image differences between the two images
# and is represented as a floating point data type in the range [0,1] 
# so we must convert the array to 8-bit unsigned integers in the range
# [0,255] before we can use it with OpenCV
diff = 255 - (diff * 255).astype("uint8")

cv2.imwrite('original_diff.png',diff)

# Perform morphological operations
kernel = cv2.getStructuringElement(cv2.MORPH_RECT,(3,3))
opening = cv2.morphologyEx(diff,cv2.MORPH_OPEN,kernel,iterations=1)
close = cv2.morphologyEx(opening,cv2.MORPH_CLOSE,iterations=1)
diff = cv2.merge([close,close,close])

# Color difference pixels
diff[np.where((diff > [10,10,50]).all(axis=2))] = [36,255,12]

cv2.imwrite('diff.png',diff)

我认为最好的方法是简单地对图像进行阈值处理并应用形态学转换。

我得到了以下结果。

阈值+形态：

选择最大的组件：

使用此代码：

cv::Mat result;
cv::Mat img = cv::imread("fOTmh.jpg");

//-- gray & smooth image
cv::cvtColor(img,result,cv::COLOR_BGR2GRAY);
cv::blur(result,cv::Size(5,5));

//-- threashold with max value of the image and smooth again!
double min,max;
cv::minMaxLoc(result,&min,&max);
cv::threshold(result,0.3*max,cv::THRESH_BINARY);
cv::medianBlur(result,7);

//-- apply Morphological Transformations
cv::Mat se = getStructuringElement(cv::MORPH_ELLIPSE,cv::Size(11,11));
cv::morphologyEx(result,cv::MORPH_DILATE,se);
cv::morphologyEx(result,cv::MORPH_CLOSE,se);

//-- find the largest component
vector<vector<cv::Point> > contours;
vector<cv::Vec4i> hierarchy;
cv::findContours(result,contours,hierarchy,cv::RETR_LIST,cv::CHAIN_APPROX_NONE);
vector<cv::Point> *l = nullptr;
for(auto &&c: contours){
    if (l==nullptr || l->size()< c.size())
        l = &c;
}

//-- expand and plot Rect around the largest component
cv::Rect r = boundingRect(*l);
r.x -=10;
r.y -=10;
r.width +=20;
r.height +=20;
cv::rectangle(img,r,cv::Scalar::all(255),3);


//-- result
cv::resize(img,img,cv::Size(),0.25,0.25);
cv::imshow("result",img);

Python代码：

import cv2 as cv

img = cv.imread("ELA_Final.jpg")

result = cv.cvtColor(img,cv.COLOR_BGR2GRAY);
result = cv.blur(result,(5,5));

minVal,maxVal,minLoc,maxLoc = cv.minMaxLoc(result)
ret,result = cv.threshold(result,0.3*maxVal,cv.THRESH_BINARY)
median = cv.medianBlur(result,7)

se = cv.getStructuringElement(cv.MORPH_ELLIPSE,(11,11));
result = cv.morphologyEx(result,cv.MORPH_DILATE,se);
result = cv.morphologyEx(result,cv.MORPH_CLOSE,se);

_,hierarchy = cv.findContours(result,cv.RETR_LIST,cv.CHAIN_APPROX_NONE)

x = []

for eachCOntor in contours:
    x.append(len(eachCOntor))
m = max(x)
p = [i for i,j in enumerate(x) if j == m]

color = (255,0) 
x,y,w,h = cv.boundingRect(contours[p[0]])
x -=10
y -=10
w +=20
h +=20
cv.rectangle(img,(x,y),(x+w,y+h),color,3)

img =  cv.resize( img,( 1500,700),interpolation = cv.INTER_AREA)
cv.imshow("result",img)
cv.waitKey(0)