import cv2 as cv
import numpy as np
from glob import glob

# the directory of the image database
database_dir = "image.orig"

def is_same_image_sift(img1_path, img2_path):
    # Load images
    img1 = cv.imread(img1_path)
    img2 = cv.imread(img2_path)
    if img1 is None or img2 is None:
        print("Error loading images!")
        return False

    # Detect keypoints and compute descriptors
    minHessian = 400
    detector = cv.SIFT_create()
    keypoints1, descriptors1 = detector.detectAndCompute(img1, None)
    keypoints2, descriptors2 = detector.detectAndCompute(img2, None)

    # Match descriptors
    matcher = cv.DescriptorMatcher_create(cv.DescriptorMatcher_BRUTEFORCE)
    matches = matcher.match(descriptors1, descriptors2)

    # Filter out low-quality matches
    matches = sorted(matches, key=lambda x: x.distance)
    min_dist = matches[0].distance
    good_matches = tuple(filter(lambda x: x.distance <= 2 * min_dist, matches))

    # Calculate similarity or distance
    if len(good_matches) > 0:
        # You can calculate the similarity or distance based on the number of good matches
        similarity = len(good_matches) / len(matches)
        print(f"Similarity: {similarity}")
        return similarity > 0.5
    else:
        print("No good matches found.")
        return False

def main():
    # img = cv.imread("beach.jpg")
    # cv.imshow("Image", img)
    # from matplotlib import pyplot as plt
    # plt.hist(img.ravel(),10,[0,256]); plt.show()
    # gray_img = cv.cvtColor(img, cv.COLOR_BGR2GRAY)
    # cv.imshow("Gray Image", gray_img)
    # cv.waitKey()

    # Example usage
    img1_path = "test_img/flower.jpg"
    img2_path = "image.orig/684.jpg"

    if is_same_image_sift(img1_path, img2_path):
        print("Images are likely the same.")
    else:
        print("Images are likely different.")

main()