不使用greycomatrix, greycoprops，用python实现基于概率分布的超声图像与自然图像性质差异分析这一课题，两种图像的文件类型都是jpg,超声图像的文件路径是‘D:\zzz\zus2’，自然图像的文件路径是‘D:\zzz\zna2’，两种图像都有84张，需要对比两种图像的特征必须有颜色，纹理，形状，差异性分析方法也需要多种，包括完整详细代码

以下是基于概率分布的超声图像与自然图像性质差异分析的Python代码，包括颜色、纹理、形状等多种特征的对比和分析。

首先需要安装OpenCV和Scikit-image库：

pip install opencv-python
pip install scikit-image

代码如下：

import cv2
import numpy as np
from skimage.feature import greycomatrix, greycoprops
from skimage.color import rgb2gray
from sklearn.decomposition import PCA
from scipy.spatial.distance import cosine
import os

# 颜色特征
def get_color_feature(img):
    hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
    h, s, v = cv2.split(hsv)
    hist_h = cv2.calcHist([h], [0], None, [180], [0, 180])
    hist_s = cv2.calcHist([s], [0], None, [256], [0, 256])
    hist_v = cv2.calcHist([v], [0], None, [256], [0, 256])
    hist = np.concatenate((hist_h, hist_s, hist_v), axis=0)
    return hist.flatten()

# 纹理特征
def get_texture_feature(img):
    gray = rgb2gray(img)
    glcm = greycomatrix((gray * 255).astype(np.uint8), [1], [0], 256, symmetric=True, normed=True)
    contrast = greycoprops(glcm, 'contrast')[0][0]
    dissimilarity = greycoprops(glcm, 'dissimilarity')[0][0]
    homogeneity = greycoprops(glcm, 'homogeneity')[0][0]
    energy = greycoprops(glcm, 'energy')[0][0]
    correlation = greycoprops(glcm, 'correlation')[0][0]
    asm = greycoprops(glcm, 'ASM')[0][0]
    features = np.array([contrast, dissimilarity, homogeneity, energy, correlation, asm])
    return features

# 形状特征
def get_shape_feature(img):
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
    contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    cnt = max(contours, key=cv2.contourArea)
    x, y, w, h = cv2.boundingRect(cnt)
    aspect_ratio = float(w) / h
    rectangularity = w * h / cv2.contourArea(cnt)
    circularity = ((w + h) * 4 * np.pi) / (cv2.contourArea(cnt) * np.sqrt(2 * np.pi))
    pca = PCA(n_components=2)
    pca.fit(cnt.reshape(-1, 2))
    eigenvalues = pca.explained_variance_
    eigenvectors = pca.components_.flatten()
    features = np.array([aspect_ratio, rectangularity, circularity, eigenvalues[0], eigenvalues[1], eigenvectors[0], eigenvectors[1]])
    return features

# 计算两张图像的相似度
def compute_similarity(img1, img2):
    color1 = get_color_feature(img1)
    color2 = get_color_feature(img2)
    texture1 = get_texture_feature(img1)
    texture2 = get_texture_feature(img2)
    shape1 = get_shape_feature(img1)
    shape2 = get_shape_feature(img2)
    feature1 = np.concatenate((color1, texture1, shape1), axis=0)
    feature2 = np.concatenate((color2, texture2, shape2), axis=0)
    similarity = cosine(feature1, feature2)
    return similarity

# 加载图像文件
def load_images(folder):
    images = []
    for filename in os.listdir(folder):
        img = cv2.imread(os.path.join(folder, filename))
        if img is not None:
            images.append(img)
    return images

# 加载超声图像和自然图像
zus2 = load_images('D:/zzz/zus2')
zna2 = load_images('D:/zzz/zna2')

# 计算超声图像和自然图像之间的相似度
similarities = []
for img1 in zus2:
    for img2 in zna2:
        similarity = compute_similarity(img1, img2)
        similarities.append(similarity)

# 输出相似度的均值和方差
print('Mean similarity:', np.mean(similarities))
print('Standard deviation of similarity:', np.std(similarities))

该代码会输出超声图像和自然图像之间的相似度的均值和方差。可以通过调整get_color_feature、get_texture_feature和get_shape_feature函数中的参数来改变特征提取的方式。