python 判断 图片是否相同

import os
    from PIL import Image
    from PIL import ImageFile
    import imagehash
      
    #仅适用于图片内容完全相同,而尺寸不同的比较
    def compare_image(img_file1, img_file2):
        if img_file1 == img_file2:
            return True
        fp1 = open(img_file1, 'rb')
        fp2 = open(img_file2, 'rb')
    
        img1 = Image.open(fp1)
        img2 = Image.open(fp2)
    
        ImageFile.LOAD_TRUNCATED_IMAGES = True
        b = img1 == img2
    
        fp1.close()
        fp2.close()
    
        return b
    




    #通过图片hash值进行比较
    def get_hash_dict(dir):
        hash_dict = {}
        image_quantity = 0
        for _, _, files in os.walk(dir):
            for i, fileName in enumerate(files):
                with open(dir + fileName, 'rb') as fp:
                    hash_dict[dir + fileName] = imagehash.average_hash(Image.open(fp))
                    image_quantity += 1
    
        return hash_dict, image_quantity
    
    def compare_image_with_hash(image_file_name_1, image_file_name_2, max_dif=0):
        """
        max_dif: 允许最大hash差值, 越小越精确,最小为0
        推荐使用
        """
        ImageFile.LOAD_TRUNCATED_IMAGES = True
        hash_1 = None
        hash_2 = None
        with open(image_file_name_1, 'rb') as fp:
            hash_1 = imagehash.average_hash(Image.open(fp))
        with open(image_file_name_2, 'rb') as fp:
            hash_2 = imagehash.average_hash(Image.open(fp))
        dif = hash_1 - hash_2
        if dif < 0:
            dif = -dif
        if dif <= max_dif:
            return True
        else:
            return False
    
    
    def compare_image_dir_with_hash(dir_1, dir_2, max_dif=0):
        """
        max_dif: 允许最大hash差值, 越小越精确,最小为0
        用于比较两个文件夹内的图片
        """
        ImageFile.LOAD_TRUNCATED_IMAGES = True
        hash_dict_1, image_quantity_1 = get_hash_dict(dir_1)
        hash_dict_2, image_quantity_2 = get_hash_dict(dir_2)
    
        if image_quantity_1 > image_quantity_2:
            tmp = image_quantity_1
            image_quantity_1 = image_quantity_2
            image_quantity_2 = tmp
    
            tmp = hash_dict_1
            hash_dict_1 = hash_dict_2
            hash_dict_2 = tmp
    
        result_dict = {}
    
        for k in hash_dict_1.keys():
            result_dict[k] = None
    
        for dif_i in range(0, max_dif + 1):
            have_none = False
    
            for k_1 in result_dict.keys():
                if result_dict.get(k_1) is None:
                    have_none = True
    
            if not have_none:
                return result_dict
    
            for k_1, v_1 in hash_dict_1.items():
                for k_2, v_2 in hash_dict_2.items():
                    sub = (v_1 - v_2)
                    if sub < 0:
                        sub = -sub
                    if sub == dif_i and result_dict.get(k_1) is None:
                        result_dict[k_1] = k_2
                        break
        return result_dict
    
    
    def main():
        print(compare_image('image1\815.jpg', 'image2\5.jpg'))
        print(compare_image_with_hash('image1\815.jpg', 'image2\5.jpg', 6))
        r = compare_image_dir_with_hash('image1\', image2\', 10)
        for k in r.keys():
            print(k, r.get(k))
    
    
    if __name__ == '__main__':
        main()

运行结果:

    False
    True
    image25.jpg image1815.jpg
    image26.jpg image1819.jpg
    image27.jpg image1900.jpg
    image28.jpg image1998.jpg
    image29.jpg image11012.jpg

图片例子

• 815.jpg
  

• 5.jpg