双十二图像分析推荐

import cv2
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity

# 加载预训练的图像特征提取模型（例如VGG16）
from tensorflow.keras.applications.vgg16 import VGG16, preprocess_input
model = VGG16(weights='imagenet', include_top=False)

def extract_features(image_path):
    img = cv2.imread(image_path)
    img = cv2.resize(img, (224, 224))  # 调整大小以适应模型输入
    img = np.expand_dims(img, axis=0)
    img = preprocess_input(img)
    features = model.predict(img)
    features = features.flatten()  # 展平特征向量
    return features

def recommend_similar_images(target_image_path, image_database):
    target_features = extract_features(target_image_path)
    similarities = []
    
    for image_path in image_database:
        features = extract_features(image_path)
        similarity = cosine_similarity([target_features], [features])[0][0]
        similarities.append((image_path, similarity))
    
    similarities.sort(key=lambda x: x[1], reverse=True)  # 按相似度降序排列
    return similarities[:5]  # 返回最相似的前5张图片

# 示例用法
image_database = ['image1.jpg', 'image2.jpg', 'image3.jpg', ...]  # 图片库路径列表
recommended_images = recommend_similar_images('target_image.jpg', image_database)
print("Recommended images:", recommended_images)