189 lines
5.5 KiB
Python
189 lines
5.5 KiB
Python
import cv2 as cv
|
|
import numpy as np
|
|
from glob import glob
|
|
|
|
# the directory of the image database
|
|
database_dir = "image.orig"
|
|
|
|
|
|
# Compute pixel-by-pixel difference and return the sum
|
|
def compareImgs(img1, img2):
|
|
# resize img2 to img1
|
|
img2 = cv.resize(img2, (img1.shape[1], img1.shape[0]))
|
|
diff = cv.absdiff(img1, img2)
|
|
return diff.sum()
|
|
|
|
|
|
def compareImgs_hist(img1, img2):
|
|
width, height = img1.shape[1], img1.shape[0]
|
|
img2 = cv.resize(img2, (width, height))
|
|
num_bins = 10
|
|
hist1 = [0] * num_bins
|
|
hist2 = [0] * num_bins
|
|
bin_width = 255.0 / num_bins + 1e-4
|
|
# compute histogram from scratch
|
|
|
|
# for w in range(width):
|
|
# for h in range(height):
|
|
# hist1[int(img1[h, w] / bin_width)] += 1
|
|
# hist2[int(img2[h, w] / bin_width)] += 1
|
|
|
|
# compute histogram by using opencv function
|
|
# https://docs.opencv.org/4.x/d6/dc7/group__imgproc__hist.html#ga4b2b5fd75503ff9e6844cc4dcdaed35d
|
|
|
|
hist1 = cv.calcHist([img1], [0], None, [num_bins], [0, 255])
|
|
hist2 = cv.calcHist([img2], [0], None, [num_bins], [0, 255])
|
|
sum = 0
|
|
for i in range(num_bins):
|
|
sum += abs(hist1[i] - hist2[i])
|
|
return sum / float(width * height)
|
|
|
|
|
|
def retrieval(choice):
|
|
output = []
|
|
# print("1: beach")
|
|
# print("2: building")
|
|
# print("3: bus")
|
|
# print("4: dinosaur")
|
|
# print("5: flower")
|
|
# print("6: horse")
|
|
# print("7: man")
|
|
# choice = input(
|
|
# "Type in the number to choose a category and type enter to confirm\n"
|
|
# )
|
|
src_input = ""
|
|
if choice == "1":
|
|
src_input = cv.imread("beach.jpg")
|
|
print("You choose: %s - beach\n" % choice)
|
|
elif choice == "2":
|
|
src_input = cv.imread("building.jpg")
|
|
print("You choose: %s - building\n" % choice)
|
|
elif choice == "3":
|
|
src_input = cv.imread("bus.jpg")
|
|
print("You choose: %s - bus\n" % choice)
|
|
elif choice == "4":
|
|
src_input = cv.imread("dinosaur.jpg")
|
|
print("You choose: %s - dinosaur\n" % choice)
|
|
elif choice == "5":
|
|
src_input = cv.imread("flower.jpg")
|
|
print("You choose: %s - flower\n" % choice)
|
|
elif choice == "6":
|
|
src_input = cv.imread("horse.jpg")
|
|
print("You choose: %s - horse\n" % choice)
|
|
elif choice == "7":
|
|
src_input = cv.imread("man.jpg")
|
|
print("You choose: %s - man\n" % choice)
|
|
else:
|
|
print("Invalid input")
|
|
exit()
|
|
|
|
min_diff = 1e50
|
|
|
|
# src_input = cv.imread("man.jpg")
|
|
# cv.imshow("Input", src_input)
|
|
|
|
# change the image to gray scale
|
|
src_gray = cv.cvtColor(src_input, cv.COLOR_BGR2GRAY)
|
|
|
|
# read image database
|
|
database = sorted(glob(database_dir + "/*.jpg"))
|
|
|
|
for img in database:
|
|
# read image
|
|
img_rgb = cv.imread(img)
|
|
# convert to gray scale
|
|
img_gray = cv.cvtColor(img_rgb, cv.COLOR_BGR2GRAY)
|
|
# compare the two images
|
|
diff = compareImgs(src_gray, img_gray)
|
|
|
|
output.append(
|
|
[int(img.replace(database_dir + "/", "").replace(".jpg", "")), img, diff]
|
|
)
|
|
# compare the two images by histogram, uncomment the following line to use histogram
|
|
# diff = compareImgs_hist(src_gray, img_gray)
|
|
# print(img, diff)
|
|
# find the minimum difference
|
|
if diff <= min_diff:
|
|
# update the minimum difference
|
|
min_diff = diff
|
|
# update the most similar image
|
|
closest_img = img_rgb
|
|
result = img
|
|
|
|
# print(
|
|
# "the most similar image is %s, the pixel-by-pixel difference is %f "
|
|
# % (result, min_diff)
|
|
# )
|
|
# closest_img
|
|
# cv.destroyAllWindows()
|
|
|
|
return output
|
|
|
|
|
|
def SIFT():
|
|
img1 = cv.imread("flower.jpg")
|
|
img2 = cv.imread("image.orig/685.jpg")
|
|
if img1 is None or img2 is None:
|
|
print("Error loading images!")
|
|
exit(0)
|
|
# -- Step 1: Detect the keypoints using SIFT Detector, compute the descriptors
|
|
minHessian = 400
|
|
detector = cv.SIFT_create()
|
|
keypoints1, descriptors1 = detector.detectAndCompute(img1, None)
|
|
keypoints2, descriptors2 = detector.detectAndCompute(img2, None)
|
|
# -- Step 2: Matching descriptor vectors with a brute force matcher
|
|
matcher = cv.DescriptorMatcher_create(cv.DescriptorMatcher_BRUTEFORCE)
|
|
matches = matcher.match(descriptors1, descriptors2)
|
|
# -- Draw matches
|
|
img_matches = np.empty(
|
|
(max(img1.shape[0], img2.shape[0]), img1.shape[1] + img2.shape[1], 3),
|
|
dtype=np.uint8,
|
|
)
|
|
cv.drawMatches(img1, keypoints1, img2, keypoints2, matches, img_matches)
|
|
# -- Show detected matches
|
|
cv.imshow("Matches: SIFT (Python)", img_matches)
|
|
cv.waitKey()
|
|
|
|
# draw good 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))
|
|
|
|
img_matches = np.empty(
|
|
(max(img1.shape[0], img2.shape[0]), img1.shape[1] + img2.shape[1], 3),
|
|
dtype=np.uint8,
|
|
)
|
|
cv.drawMatches(
|
|
img1,
|
|
keypoints1,
|
|
img2,
|
|
keypoints2,
|
|
good_matches,
|
|
img_matches,
|
|
flags=cv.DrawMatchesFlags_NOT_DRAW_SINGLE_POINTS,
|
|
)
|
|
|
|
# -- Show detected matches
|
|
cv.imshow("Good Matches: SIFT (Python)", img_matches)
|
|
cv.waitKey()
|
|
|
|
|
|
def test_performance(number):
|
|
# print("1: Image retrieval demo")
|
|
# print("2: SIFT demo")
|
|
|
|
if number == 1:
|
|
retrieval_results = retrieval("1")
|
|
from pprint import pprint
|
|
|
|
pprint(retrieval_results)
|
|
elif number == 2:
|
|
SIFT()
|
|
# pass
|
|
else:
|
|
print("Invalid input")
|
|
exit()
|
|
|
|
|
|
test_performance(1)
|