duplicate_detector.py

import numpy as np
from tensorflow.keras.applications import ResNet50
from tensorflow.keras.preprocessing import image
from tensorflow.keras.applications.resnet50 import preprocess_input
from sklearn.metrics.pairwise import cosine_similarity
import os

# Load the pre-trained ResNet50 model
model = ResNet50(weights='imagenet', include_top=False, pooling='avg')


# Function to extract feature vector from an image
def extract_features(img_path, model):
    img = image.load_img(img_path, target_size=(224, 224))
    img_data = image.img_to_array(img)
    img_data = np.expand_dims(img_data, axis=0)
    img_data = preprocess_input(img_data)
    features = model.predict(img_data)
    return features.flatten()


# Function to find and count duplicates
def find_duplicates(image_dir, threshold=0.9):
    image_features = {}
    for img_file in os.listdir(image_dir):
        img_path = os.path.join(image_dir, img_file)
        features = extract_features(img_path, model)
        image_features[img_file] = features

    feature_list = list(image_features.values())
    file_list = list(image_features.keys())

    num_images = len(file_list)
    similarity_matrix = np.zeros((num_images, num_images))

    for i in range(num_images):
        for j in range(i, num_images):
            if i != j:
                similarity = cosine_similarity(
                    [feature_list[i]],
                    [feature_list[j]]
                )[0][0]
                similarity_matrix[i][j] = similarity
                similarity_matrix[j][i] = similarity

    duplicates = set()
    for i in range(num_images):
        for j in range(i + 1, num_images):
            if similarity_matrix[i][j] > threshold:
                duplicates.add(file_list[j])

    return len(duplicates), duplicates


if __name__ == "__main__":
    import sys

    image_dir = sys.argv[1] if len(sys.argv) > 1 else './images'
    threshold = float(sys.argv[2]) if len(sys.argv) > 2 else 0.9

    count, duplicates = find_duplicates(image_dir, threshold)
    print(f"Duplicate Images Count: {count}")
    for duplicate in duplicates:
        print(duplicate)