图像去重通常指的是完全相同的图像,即内容完全相同,颜色、尺寸、方向等都相同。但是在实际应用中,也有相似图像去重的需求,即内容大致相同,颜色、尺寸、方向等可能有所不同。因此,图像去重指的可以是完全一样的图像,也可以是相似的图像。
图像去重的方法有以下几种:
这些方法的选择取决于图像去重的具体需求和数据的特征。
import cv2
import numpy as np
def compare_images(image1, image2):
# 计算图像的直方图
hist1 = cv2.calcHist([image1], [0], None, [256], [0, 256])
hist2 = cv2.calcHist([image2], [0], None, [256], [0, 256])
# 计算直方图的相似度
similarity = cv2.compareHist(hist1, hist2, cv2.HISTCMP_CORREL)
return similarity
# 读入两张图片
img1 = cv2.imread('image1.jpg')
img2 = cv2.imread('image2.jpg')
# 计算两张图片的相似度
similarity = compare_images(img1, img2)
# 根据相似度判断图片是否重复
if similarity > 0.95:
print("Images are duplicates")
else:
print("Images are not duplicates")
import cv2
import hashlib
def calculate_hash(image):
# 调整图像大小
image = cv2.resize(image, (9, 8), interpolation = cv2.INTER_CUBIC)
# 转换为灰度图像
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# 计算哈希值
hash_value = 0
for i in range(8):
for j in range(8):
if gray[i, j] > gray[i, j + 1]:
hash_value += 1 << (i * 8 + j)
return hash_value
# 读入两张图片
img1 = cv2.imread('image1.jpg')
img2 = cv2.imread('image2.jpg')
# 计算图片的哈希值
hash1 = calculate_hash(img1)
hash2 = calculate_hash(img2)
# 判断图片是否重复
if hash1 == hash2:
print("Images are duplicates")
else:
print("Images are not duplicates")
import cv2
def extract_features(image):
# 使用 ORB 算法提取图像的特征点
orb = cv2.ORB_create()
keypoints, descriptors = orb.detectAndCompute(image, None)
return keypoints, descriptors
# 读入两张图片
img1 = cv2.imread('image1.jpg')
img2 = cv2.imread('image2.jpg')
# 提取图像的特征点和描述符
kp1, des1 = extract_features(img1)
kp2, des2 = extract_features(img2)
# 匹配两张图片的特征点
bf = cv2.BFMatcher(cv2.NORM_HAMMING, crossCheck = True)
matches = bf.match(des1, des2)
# 计算匹配到的特征点数量
match_count = len(matches)
# 判断图片是否重复
if match_count > 10:
print("Images are duplicates")
else:
print("Images are not duplicates")
import cv2
import numpy as np
from sklearn.neighbors import KNeighborsClassifier
# Load the images and resize them to a fixed size
images = []
labels = []
for i in range(10):
img = cv2.imread(f'image_{i}.jpg')
img = cv2.resize(img, (128, 128))
images.append(img)
labels.append(i % 5)
# Extract features from the images using a feature extractor
def extract_features(images):
features = []
for img in images:
hist = cv2.calcHist([img], [0, 1, 2], None, [8, 8, 8], [0, 256, 0, 256, 0, 256])
hist = hist.flatten()
features.append(hist)
return np.array(features)
features = extract_features(images)
# Train a KNN classifier on the features
clf = KNeighborsClassifier(n_neighbors=1)
clf.fit(features, labels)
# Use the classifier to predict the label of a new image
new_img = cv2.imread('new_image.jpg')
new_img = cv2.resize(new_img, (128, 128))
new_features = extract_features([new_img])
predicted_label = clf.predict(new_features)
import os
import cv2
import numpy as np
def calc_hist(image):
"""Calculate the histogram of an image."""
hist = cv2.calcHist([image], [0], None, [256], [0, 256])
return hist.flatten()
def find_duplicates(path):
"""Find duplicate images in a directory."""
image_hashes = {}
duplicates = []
for filename in os.listdir(path):
file_path = os.path.join(path, filename)
if os.path.isfile(file_path):
try:
image = cv2.imread(file_path, 0)
hist = calc_hist(image)
hash = np.array_str(hist)
if hash in image_hashes:
duplicates.append((file_path, image_hashes[hash]))
else:
image_hashes[hash] = file_path
except:
pass
return duplicates
dp = find_duplicates('data')
print(dp)