파이썬 이미지 비교

이미지 비교

import cv2

# Load the two images

img1 = cv2.imread('image1.jpg')

img2 = cv2.imread('image2.jpg')

# Calculate the absolute difference between the two images

diff = cv2.absdiff(img1, img2)

# Display the difference image

cv2.imshow('Difference Image', diff)

cv2.waitKey(0)

cv2.destroyAllWindows()

2 이미지 비교 2번째[편집]

import cv2

# Load the two images
img1 = cv2.imread('image1.jpg')
img2 = cv2.imread('image2.jpg')

# Convert the images to grayscale
gray_img1 = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
gray_img2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)

# Calculate the structural similarity index (SSIM) between the two images
ssim = cv2.compare_ssim(gray_img1, gray_img2)

# Display the SSIM value
print("The SSIM value between the two images is: {}".format(ssim))

3 이미지 비교 3번째 [편집]

from PIL import Image, ImageChops

# Load the images

image1 = Image.open("image1.jpg")

image2 = Image.open("image2.jpg")

# Compare the images

diff = ImageChops.difference(image1, image2)

# Check if the images are the same

if diff.getbbox() is None:
    print("The images are the same")
else:
    print("The images are different")

4 이미지비교 3[편집]

from PIL import Image
import numpy as np
from skimage.metrics import structural_similarity as ssim

def mse(imageA, imageB):
    err = np.sum((imageA.astype("float") - imageB.astype("float")) ** 2)
    err /= float(imageA.shape[0] * imageA.shape[1])
    return err

def compare_images(image_path1, image_path2):
    image1 = Image.open(image_path1).convert("L")  # Convert to grayscale
    image2 = Image.open(image_path2).convert("L")

    image1_np = np.array(image1)
    image2_np = np.array(image2)

    mse_value = mse(image1_np, image2_np)
    ssim_value = ssim(image1_np, image2_np)

    return mse_value, ssim_value

if __name__ == "__main__":
    image_path1 = "path/to/your/image1.jpg"
    image_path2 = "path/to/your/image2.jpg"

    mse_value, ssim_value = compare_images(image_path1, image_path2)

    print(f"MSE: {mse_value}")
    print(f"SSIM: {ssim_value}")

Replace the image_path1 and image_path2 with the paths to your images. The MSE is a measure of the difference between the two images, with a smaller value indicating a higher similarity. The SSIM is a measure of structural similarity, with a value between -1 and 1, where a higher value indicates higher similarity.

The code above will convert the images to grayscale before comparing them. If you want to compare images in color, remove the .convert("L") and update the ssim function call to ssim(image1_np, image2_np, multichannel=True).

Remember that this approach works best for images of the same size. If you need to compare images with different sizes, you should resize them before performing the comparison.

5 이미지 비교[편집]

import numpy as np
import tensorflow as tf
from tensorflow.keras.applications.resnet50 import ResNet50, preprocess_input
from tensorflow.keras.preprocessing import image as kimage

def load_and_preprocess_image(image_path, target_size=(224, 224)):
    img = kimage.load_img(image_path, target_size=target_size)
    img_array = kimage.img_to_array(img)
    img_array = np.expand_dims(img_array, axis=0)
    img_array = preprocess_input(img_array)
    return img_array

def extract_features(img_array, model):
    features = model.predict(img_array)
    features = features.flatten()
    return features

def cosine_similarity(vecA, vecB):
    dot_product = np.dot(vecA, vecB)
    normA = np.linalg.norm(vecA)
    normB = np.linalg.norm(vecB)
    return dot_product / (normA * normB)

# Load pre-trained ResNet-50 model without the top layer
model = ResNet50(weights="imagenet", include_top=False, pooling='avg')

image1_path = "path/to/image1.jpg"
image2_path = "path/to/image2.jpg"

image1 = load_and_preprocess_image(image1_path)
image2 = load_and_preprocess_image(image2_path)

features1

파이썬 이미지 비교

DB CAFE

목차

1 이미지 비교 1번째 [편집]

2 이미지 비교 2번째[편집]

3 이미지 비교 3번째 [편집]

4 이미지비교 3[편집]

5 이미지 비교[편집]