# coding: utf-8 # The code is written by Linghui import numpy as np from skimage import data from matplotlib import pyplot as plt import get_glcm import time from PIL import Image import spectral import os import warnings warnings.filterwarnings('ignore') # 使用get_glcm模块进行GLCM计算 def main(): pass def load_hyperspectral_data(image_path, band_index=None): """ 加载高光谱数据并可选地提取指定波段 参数: - image_path: 高光谱图像文件路径 - band_index: 要提取的波段索引，如果为None则返回整个图像 返回: - img: 处理后的图像数据 - h, w: 图像尺寸 """ print(f'正在读取高光谱图像: {image_path}') try: # 使用spectral库读取ENVI格式 img_obj = spectral.open_image(image_path) hyperspectral_data = img_obj.load() print(f'使用spectral库读取成功，数据形状: {hyperspectral_data.shape}') except Exception as e: print(f'spectral库读取失败: {e}') raise ValueError(f"无法读取图像文件: {image_path}") # 检查数据维度 if len(hyperspectral_data.shape) != 3: raise ValueError(f"高光谱数据应该是3维的，当前形状: {hyperspectral_data.shape}") h, w, bands = hyperspectral_data.shape print(f'图像尺寸: {h}x{w}, 波段数: {bands}') # 如果指定了波段索引，提取该波段 if band_index is not None: if band_index < 0 or band_index >= bands: raise ValueError(f"波段索引 {band_index} 超出范围 [0, {bands-1}]") print(f'提取波段 {band_index}...') img = hyperspectral_data[:, :, band_index].astype(np.float32) # 归一化到0-255范围 img_min, img_max = img.min(), img.max() if img_max > img_min: img = np.uint8(255.0 * (img - img_min) / (img_max - img_min)) else: img = np.zeros_like(img, dtype=np.uint8) print(f'提取的波段数据范围: [{img_min:.2f}, {img_max:.2f}] -> [0, 255]') else: # 如果没有指定波段，返回第一个波段作为示例 print('未指定波段，使用第一个波段...') img = hyperspectral_data[:, :, 0].astype(np.float32) img_min, img_max = img.min(), img.max() if img_max > img_min: img = np.uint8(255.0 * (img - img_min) / (img_max - img_min)) else: img = np.zeros_like(img, dtype=np.uint8) return img, h, w if __name__ == '__main__': main() start = time.time() print('---------------0. Parameter Setting-----------------') nbit = 64 # gray levels mi, ma = 0, 255 # max gray and min gray slide_window = 7 # sliding window # step = [2, 4, 8, 16] # step # angle = [0, np.pi/4, np.pi/2, np.pi*3/4] # angle or direction step = [2] angle = [0] # 指定波段索引（可以修改） band_index = 25 # 要处理的波段索引，从0开始 print('-------------------1. Load Data---------------------') # 修改为高光谱图像路径 image_path = r"C:\Program Files\Spectronon3\_internal\examples\leaf_small.bip.hdr" # image_path = r"./test.tif" # 备用的TIFF图像路径 # 检查文件是否存在 if not os.path.exists(image_path): print(f"警告: 指定的图像文件不存在: {image_path}") print("请确保文件路径正确，或使用其他可用的图像文件") exit(1) # 加载高光谱数据 img, h, w = load_hyperspectral_data(image_path, band_index) print('------------------2. 计算GLCM特征---------------------') img = img.squeeze() # 使用get_glcm计算GLCM特征 glcm = get_glcm.calcu_glcm(img, mi, ma, nbit, slide_window, step, angle) print('GLCM计算完成！') print('-----------------3. 提取纹理特征-------------------') # 提取纹理特征用于显示 # 只计算最后一个step和angle的特征用于显示 i, j = len(step)-1, len(angle)-1 # 使用最后一个配置 glcm_cut = glcm[:, :, i, j, :, :] mean = get_glcm.calcu_glcm_mean(glcm_cut, nbit) variance = get_glcm.calcu_glcm_variance(glcm_cut, nbit) homogeneity = get_glcm.calcu_glcm_homogeneity(glcm_cut, nbit) contrast = get_glcm.calcu_glcm_contrast(glcm_cut, nbit) dissimilarity = get_glcm.calcu_glcm_dissimilarity(glcm_cut, nbit) entropy = get_glcm.calcu_glcm_entropy(glcm_cut, nbit) energy = get_glcm.calcu_glcm_energy(glcm_cut, nbit) correlation = get_glcm.calcu_glcm_correlation(glcm_cut, nbit) Auto_correlation = get_glcm.calcu_glcm_Auto_correlation(glcm_cut, nbit) print('---------------4. Display and Result----------------') print(f'使用的波段: {band_index}') print(f'GLCM参数: distances={step}, angles={[f"{a*180/np.pi:.0f}°" for a in angle]}') plt.figure(figsize=(10, 4.5)) font = {'family' : 'Times New Roman', 'weight' : 'normal', 'size' : 12, } plt.subplot(2,5,1) plt.tick_params(labelbottom=False, labelleft=False) plt.axis('off') plt.imshow(img, cmap ='gray') plt.title(f'Band {band_index}', font) plt.subplot(2,5,2) plt.tick_params(labelbottom=False, labelleft=False) plt.axis('off') plt.imshow(mean, cmap ='gray') plt.title('Mean', font) plt.subplot(2,5,3) plt.tick_params(labelbottom=False, labelleft=False) plt.axis('off') plt.imshow(variance, cmap ='gray') plt.title('Variance', font) plt.subplot(2,5,4) plt.tick_params(labelbottom=False, labelleft=False) plt.axis('off') plt.imshow(homogeneity, cmap ='gray') plt.title('Homogeneity', font) plt.subplot(2,5,5) plt.tick_params(labelbottom=False, labelleft=False) plt.axis('off') plt.imshow(contrast, cmap ='gray') plt.title('Contrast', font) plt.subplot(2,5,6) plt.tick_params(labelbottom=False, labelleft=False) plt.axis('off') plt.imshow(dissimilarity, cmap ='gray') plt.title('Dissimilarity', font) plt.subplot(2,5,7) plt.tick_params(labelbottom=False, labelleft=False) plt.axis('off') plt.imshow(entropy, cmap ='gray') plt.title('Entropy', font) plt.subplot(2,5,8) plt.tick_params(labelbottom=False, labelleft=False) plt.axis('off') plt.imshow(energy, cmap ='gray') plt.title('Energy', font) plt.subplot(2,5,9) plt.tick_params(labelbottom=False, labelleft=False) plt.axis('off') plt.imshow(correlation, cmap ='gray') plt.title('Correlation', font) plt.subplot(2,5,10) plt.tick_params(labelbottom=False, labelleft=False) plt.axis('off') plt.imshow(Auto_correlation, cmap ='gray') plt.title('Auto Correlation', font) plt.tight_layout(pad=0.5) # 创建输出文件名，包含波段信息 output_filename = f'GLCM_Features_Band{band_index}.png' plt.savefig(output_filename , format='png' , bbox_inches = 'tight' , pad_inches = 0 , dpi=300) print(f'结果图像已保存到: {output_filename}') end = time.time() print('Code run time:', end - start)