SAR/test_data/xie/feature_lbp.py

import cv2
import numpy as np
import sys
import matplotlib.pyplot as plt
from skimage import feature
import os
# 定义LBP算子的计算函数
def calculate_lbp_pixel(center, pixels):
    lbp_code = 0
    for i, pixel in enumerate(pixels):
        lbp_code |= (pixel >= center) << i
    return lbp_code

# 定义LBP特征提取函数
def extract_lbp_features(image, radius, num_points):
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    height, width = gray.shape
    lbp_image = np.zeros((height, width), dtype=np.uint8)

    for y in range(radius, height - radius):
        for x in range(radius, width - radius):
            center = gray[y, x]
            pixels = [
                gray[y - radius, x - radius],
                gray[y - radius, x],
                gray[y - radius, x + radius],
                gray[y, x + radius],
                gray[y + radius, x + radius],
                gray[y + radius, x],
                gray[y + radius, x - radius],
                gray[y, x - radius]
            ]
            lbp_code = calculate_lbp_pixel(center, pixels)
            lbp_image[y, x] = lbp_code

    hist = np.histogram(lbp_image, bins=np.arange(0, num_points + 2), range=(0, num_points + 1))[0]
    hist = hist.astype("float")
    hist /= (hist.sum() + 1e-6)  # 归一化

    return hist

# 加载图像
# image = cv2.imread('D:\\hiddz\\SAR\\test_data\\TEST\\2S1\\HB14937.JPG')

# # 设置LBP算子的半径和邻域点数
# radius = 1
# num_points = 8 * radius
#
# # 提取LBP特征
# lbp_features = extract_lbp_features(image, radius, num_points)
#
# # 打印特征向量
# print("LBP特征向量:")
# print(lbp_features)
#
# image_path = 'D:\\hiddz\\SAR\\test_data\\TEST\\A11\\HB14931.JPG'
#
# # 读取图像并转换为灰度图
# image = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE)
# # 计算LBP特征
# radius = 1
# n_points = 8 * radius
# lbp_image = feature.local_binary_pattern(image, n_points, radius, method='uniform')
# cv2.imwrite('image_features/image_with_lbp_keypoints.jpg', lbp_image)
# # 显示原始图像和LBP图像
#
# plt.imshow(lbp_image, cmap='gray')
# plt.title('LBP Image')
# plt.show()

def process_image(image_path):
    image = cv2.imread(image_path)

    # 设置LBP算子的半径和邻域点数
    radius = 1
    num_points = 8 * radius

    # 提取LBP特征
    lbp_features = extract_lbp_features(image, radius, num_points)

    # 读取图像并转换为灰度图
    image = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE)
    # 计算LBP特征
    radius = 1
    n_points = 8 * radius
    lbp_image = feature.local_binary_pattern(image, n_points, radius, method='uniform')
    cv2.imwrite('image_features/image_with_lbp_keypoints.jpg', lbp_image)
    # LBP图像
    plt.imshow(lbp_image, cmap='gray')
    plt.title('LBP Image')

    folder_name = os.path.basename(os.path.dirname(image_path))

    # 创建保存图像的文件夹
    save_folder = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'lbp', folder_name)
    os.makedirs(save_folder, exist_ok=True)

    # 保存图像
    save_path = os.path.join(save_folder, 'lbp_' + os.path.basename(image_path))
    plt.imsave(save_path, lbp_image, cmap='gray')
    print(save_path)

if __name__ == "__main__":

    if len(sys.argv) != 2:
        sys.exit(1)

    image_path = sys.argv[1]
    process_image(image_path)