Tampering detection by using sobel edge in processing - processing

Question

I have to use Sobel edge detection to detect how an image has been tampered with. I have been able to implement the edge filter, but have not been able to figure out how to use it to detect tampering. I want to show the tampering by highlighting the region that has been tampered with in another color.
Can someone help please?
PImage img, edgeImg;
int[][] sobelx = { { -1, -2, -1 }, { 0, 0, 0 }, { 1, 2, 1 } };
int[][] sobely = { { -1, 0, 1 }, { -2, 0, 2 }, { -1, 0, 1 } };
void setup() {
img = loadImage("face1.jpg");
size(img.width, img.height);
edgeImg = createImage(img.width, img.height, RGB);
}
void draw() {
image(img, 0, 0);
int matrixsize = 3;
loadPixels();
img.loadPixels();
int loc = 0;
for (int x = 1; x < img.width - 1; x++) {
for (int y = 1; y < img.height - 1; y++) {
loc = x + y * img.width;
int sx = convolution(x, y, sobelx, matrixsize, img);
int sy = convolution(x, y, sobely, matrixsize, img);
int sum = abs(sy) + abs(sx);
sum = constrain(sum, 0, 255);
edgeImg.pixels[loc] = sum;
}
}
edgeImg.updatePixels();
image(edgeImg, 0, 0);
filter(THRESHOLD, 0.8);
}
int convolution(int x, int y, int [][] mat, int matrixsize, PImage img) {
float rtotal = 0.0;
float gtotal = 0.0;
float btotal = 0.0;
int total = 0;
int offset = matrixsize/2;
for(int i=0; i<matrixsize; i++) {
for(int j=0; j<matrixsize; j++) {
int xloc = x + i - offset;
int yloc = y + j - offset;
int loc = xloc + img.width*yloc;
loc = constrain(loc,0,img.pixels.length - 1);
rtotal = rtotal + red(img.pixels[loc])*mat[i][j];
gtotal = gtotal + green(img.pixels[loc])*mat[i][j];
btotal = btotal + blue(img.pixels[loc])*mat[i][j];
total = total + int(brightness(img.pixels[loc])*mat[i][j]);
}
}
rtotal = constrain(rtotal, 0, 255);
gtotal = constrain(gtotal, 0, 255);
btotal = constrain(btotal, 0, 255);
return total;
}

Answer 1

I don't know how the algorithm can be used for your particular purpose, but I would guess you would need to run the same filter to the original image and compare the results.
PImage original = loadImage("face1.jpg");
PImage edgeImg; // previously created
original.loadPixels();
edgeImg.loadPixels();
for (int i=0; i<original.pixels.length; i++) {
color origPx = original.pixels[i];
color edgePx = edgeImg.pixels[i];
// compare red values, since the edgeImg is B&W
if ( (origPx >> 16 & 0xFF) != (edgePx >> 16 & 0xFF) ) {
// don't match? do something!
}
}