SAR/test_data/xie/feature_glcm.py

# import numpy as np
# import cv2
# import sys
# import os
# from skimage.feature import graycomatrix, graycoprops, greycoprops, greycomatrix
# from skimage import io, color, img_as_ubyte
# import matplotlib.pyplot as plt
# # 读取图像
# image = io.imread('HB03333.jpeg')
#
# # 将图像转换为灰度
# gray_image = io.imread('D:\\hiddz\\SAR\\test_data\\TEST\\A11\\HB14931.JPG')
# gray_image = img_as_ubyte(gray_image)
#
# # 定义GLCM参数
# distances = [1, 2, 3, 4]  # 邻距离
# angles = [0, np.pi/4, np.pi/2, 3*np.pi/4]  # 邻角度
#
# # 计算GLCM
# glcm = graycomatrix(gray_image, distances=distances, angles=angles, symmetric=True, normed=True)
#
# # 计算GLCM特征
# contrast = graycoprops(glcm, prop='contrast')
# dissimilarity = graycoprops(glcm, prop='dissimilarity')
# homogeneity = graycoprops(glcm, prop='homogeneity')
# energy = graycoprops(glcm, prop='energy')
# correlation = graycoprops(glcm, prop='correlation')
#
# # 打印GLCM特征
# print("Contrast:", contrast)
# print("Dissimilarity:", dissimilarity)
# print("Homogeneity:", homogeneity)
# print("Energy:", energy)
# print("Correlation:", correlation)
# # 可视化GLCM特征
#
# plt.imshow(energy, cmap='hot')
# plt.title('GLCM Energy Map')
# custom_xticks = np.arange(4)
# custom_xticklabels = ['0', 'pi/4', 'pi/2', '3pi/4']  # 自定义刻度标签，与刻度位置一一对应
# custom_yticklables = ['1', '2', '3', '4']
# plt.yticks(custom_xticks, custom_yticklables)
# plt.xticks(custom_xticks, custom_xticklabels)  # 设置刻度位置和标签
# plt.xlabel('Angles')
# plt.ylabel('distance')
# plt.colorbar()
#
# plt.savefig('D:\\hiddz\\SAR\\test_data\\TEST\A11')
# plt.show()
# #
#
# def process_image(image_path):
#     gray_image = io.imread(image_path)
#     gray_image = img_as_ubyte(gray_image)
#
#     distances = [1, 2, 3, 4]
#     angles = [0, np.pi / 4, np.pi / 2, 3 * np.pi / 4]  # 邻角度
#
#     # 计算GLCM
#     glcm = graycomatrix(gray_image, distances=distances, angles=angles, symmetric=True, normed=True)
#
#     # 计算GLCM特征
#     contrast = graycoprops(glcm, prop='contrast')
#     dissimilarity = graycoprops(glcm, prop='dissimilarity')
#     homogeneity = graycoprops(glcm, prop='homogeneity')
#     energy = graycoprops(glcm, prop='energy')
#     correlation = graycoprops(glcm, prop='correlation')
#
#     plt.imshow(energy, cmap='hot')
#     plt.title('GLCM Energy Map')
#     custom_xticks = np.arange(4)
#     custom_xticklabels = ['0', 'pi/4', 'pi/2', '3pi/4']  # 自定义刻度标签，与刻度位置一一对应
#     custom_yticklables = ['1', '2', '3', '4']
#     plt.yticks(custom_xticks, custom_yticklables)
#     plt.xticks(custom_xticks, custom_xticklabels)  # 设置刻度位置和标签
#     plt.xlabel('Angles')
#     plt.ylabel('distance')
#     plt.colorbar()
#     plt.show()

    # folder_name = os.path.basename(os.path.dirname(image_path))
    #
    # save_folder = os.path.join(os.path.dirname(os.path.abspath(__path__)), 'glcm', folder_name)
    # os.makedirs(save_folder, exist_ok=True)
    #
    # save_path = os.path.join(save_folder, 'glcm_', os.path.basename(image_path))
    # plt.imsave(save_path, energy, 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)

import numpy as np
from skimage import io, img_as_ubyte
from skimage.feature import greycomatrix, greycoprops
import matplotlib.pyplot as plt
from matplotlib.backends.backend_agg import FigureCanvasAgg as FigureCanvas

def process_image(image_path):
    gray_image = io.imread(image_path)
    gray_image = img_as_ubyte(gray_image)

    distances = [1, 2, 3, 4]
    angles = [0, np.pi / 4, np.pi / 2, 3 * np.pi / 4]  # 邻角度

    # 计算GLCM
    glcm = greycomatrix(gray_image, distances=distances, angles=angles, symmetric=True, normed=True)

    # 计算GLCM特征
    contrast = greycoprops(glcm, prop='contrast')
    dissimilarity = greycoprops(glcm, prop='dissimilarity')
    homogeneity = greycoprops(glcm, prop='homogeneity')
    energy = greycoprops(glcm, prop='energy')
    correlation = greycoprops(glcm, prop='correlation')

    fig, ax = plt.subplots()
    ax.imshow(energy, cmap='hot')
    ax.set_title('GLCM Energy Map')
    custom_xticks = np.arange(4)
    custom_xticklabels = ['0', 'pi/4', 'pi/2', '3pi/4']  # 自定义刻度标签，与刻度位置一一对应
    custom_yticklables = ['1', '2', '3', '4']
    ax.set_yticks(custom_xticks)
    ax.set_yticklabels(custom_yticklables)
    ax.set_xticks(custom_xticks)
    ax.set_xticklabels(custom_xticklabels)
    ax.set_xlabel('Angles')
    ax.set_ylabel('distance')
    plt.colorbar()

    # 将图形保存为图像
    canvas = FigureCanvas(fig)
    canvas.draw()
    bbox = fig.get_window_extent().transformed(fig.dpi_scale_trans.inverted())
    width, height = bbox.width * fig.dpi, bbox.height * fig.dpi
    image = np.frombuffer(canvas.tostring_rgb(), dtype='unit8').reshape(int(height), int(width), 3)
    plt.imsave('energy_map.png', image)


if __name__ == '__main__':
    image_path = 'D:\\hiddz\\SAR\\test_data\\TEST\\A11\\HB14931.JPG'
    process_image(image_path)