其中的直方图的绘画部分要注意，只写了部分的直方图代码

###直接调用skimag库中的函数BLP提取纹理
from skimage import data

import matplotlib.pyplot as plt

import cv2

from skimage.feature import local_binary_pattern

image = data.camera()

plt.subplot(2,3,1)

plt.title('original')

plt.imshow(image,cmap='gray')

#不同方法的BLP展示

radius = 3# LBP算法中范围半径的取值

n_points = 8 * radius#领域内采样点数

#选择四种不同的LBP方法提取纹理

method = 'default'#灰度但不是旋转不变的

lbp = local_binary_pattern(image, n_points, radius,method)#LBP表达式

plt.subplot(232)

plt.imshow(lbp, plt.cm.gray)

plt.title('default BLP')



method = 'uniform'#改进的灰度和旋转不变

lbp = local_binary_pattern(image, n_points, radius,method)

plt.subplot(233)

plt.imshow(lbp, plt.cm.gray)

plt.title('uniform BLP')



method = 'var'#旋转但不是灰度不变的

lbp = local_binary_pattern(image, n_points, radius,method)

plt.subplot(234)

plt.imshow(lbp, plt.cm.gray)

plt.title('var BLP')



method = 'ror'#灰度和旋转不变

lbp = local_binary_pattern(image, n_points, radius,method)

plt.subplot(235)

plt.imshow(lbp, plt.cm.gray)

plt.title('ror BLP')

##加了一个边缘图像对比纹理图像

edges = filters.sobel(image)

plt.subplot(236)

plt.imshow(edges, plt.cm.gray)

plt.title('edge')





##############BLP圆形算子提取纹理，程序unit16

import numpy as np

import cv2

import matplotlib.pyplot as plt

import math

from skimage import data

def circular_LBP(src, radius, n_points):

    height = src.shape[0]

    width = src.shape[1]

    # dst = np.zeros([height, width], dtype=np.uint8)

    dst = src.copy()

    src.astype(dtype=np.float32)

    dst.astype(dtype=np.float32)



    neighbours = np.zeros((1, n_points), dtype=np.uint8)

    lbp_value = np.zeros((1, n_points), dtype=np.uint8)

    for x in range(radius, width - radius ):

        for y in range(radius, height - radius ):

            lbp = 0.

            for n in range(n_points):

                theta = float(2 * np.pi * n) / n_points

                x_n = x + radius * np.cos(theta)#计算采样点的坐标

                y_n = y - radius * np.sin(theta)



                # 向下取整

                x1 = int(math.floor(x_n))

                y1 = int(math.floor(y_n))

                # 向上取整

                x2 = int(math.ceil(x_n))

                y2 = int(math.ceil(y_n))



                # 将坐标映射到0-1之间

                tx = np.abs(x - x1)

                ty = np.abs(y - y1)



                # 根据0-1之间的x，y的权重计算公式计算权重

                w1 = (1 - tx) * (1 - ty)

                w2 = tx * (1 - ty)

                w3 = (1 - tx) * ty

                w4 = tx * ty



                # 根据双线性插值公式计算第k个采样点的灰度值

                neighbour = src[y1, x1] * w1 + src[y2, x1] * w2 + src[y1, x2] * w3 + src[y2, x2] * w4

                neighbours[0, n] = neighbour

            center = src[y, x]

            # ######确定中心值

            for n in range(n_points):

                if neighbours[0, n] > center:

                    lbp_value[0, n] = 1

                else:

                    lbp_value[0, n] = 0

            # 取出所有的中心值

            for n in range(n_points):

                lbp += lbp_value[0, n] * 2**n

                # print('lbp_value[0, n] * 2**n : {}'.format(lbp_value[0, n] * 2**n))

            # LBP值归一化处理，并把灰度值转到0-255

            dst[y, x] = int(lbp / (2**n_points-1) * 255)

return dst

def show_basic_hist(a): #画lbp的直方图      

    hist = cv.calcHist([a],[0],None,[256],[0,256])

    #hist = cv.normalize(hist,hist)

    plt.plot(hist, color='r')

    plt.xlim([0,256])   

img2 = cv.imread("D:\honeycombed_0169.jpg",0)

plt.title('original hist')

show_basic_hist(img2)

if __name__ == '__main__':

    img = data.camera()

    dst18 = circular_LBP(img, radius=1, n_points=8)

    dst38 = circular_LBP(img, radius=3, n_points=8)

    dst316 = circular_LBP(img, radius=3, n_points=16)

    plt.subplot(1,4,1)

    plt.title('original')

    plt.imshow(img,cmap='gray')

    plt.subplot(1,4,2)

    plt.title('dst18')

    plt.imshow(dst18)

    plt.subplot(1,4,3)

    plt.title('dst38')

    plt.imshow(dst38)

    plt.subplot(1,4,4)

    plt.title('dst316')

    plt.imshow(dst316)



##########Untitled15 2.Gabor滤波器提取纹理特征

import cv2

import numpy as np

import pylab as pl

from PIL import Image

#构建Gabor滤波器

def build_filters():

    filters = []

    ksize = [7,9,11,13,15,17] #gabor有尺度 6个

    lamda = np.pi/2.0 # 设置波长

    for theta in np.arange(0,np.pi,np.pi/4): #gabor方向 0 45 90 135

        for k in range(6):

            kern= cv2.getGaborKernel((ksize[k],ksize[k]),1.0,theta,lamda,0.5,0,ktype=cv2.CV_32F)#生成Gabor 滤波核，即模板

            kern/= 1.5*kern.sum()#规范化内核，确保内核不会改变整体亮度           

  filters.append(kern)

 for temp in range(len(filters)):

 plt.subplot(4, 6, temp + 1)

   plt.imshow(filters[temp])

 plt.show()  

    return filters

#滤波过程

def process(img,filters):

    accum = np.zeros_like(img)#构造矩阵

    for kern in filters:

        fimg = cv2.filter2D(img,cv2.CV_8UC3,kern)#自定义卷积核实现卷积    np.maximum(accum,fimg,accum)#依次比较取最大

    return accum

#特征图生成并显示

def getGabor(img,filters):

    image = Image.open(img)

    img_ndarray = np.asarray(image)#图像转换成数组

    res = [] #滤波结果

    for i in range(len(filters)):

        res1 = process(img_ndarray,filters[i])

        res.append(np.asarray(res1))

    pl.figure(2)

    for temp in range(len(res)):

        pl.subplot(4,6,temp+1)  #画4*6格子

        pl.imshow(res[temp],cmap='gray')

        show_basic_hist(res[temp])

    pl.show()

return res

def show_basic_hist(a): #画Garbor的直方图      

hist = cv.calcHist([a],[0],None,[256],[0,256])

 #hist = cv.normalize(hist,hist)

plt.plot(hist, color='r')

plt.xlim([0,256])

plt.show()

img2 = cv.imread("D:\honeycombed_0169.jpg",0)

show_basic_hist(img2)

plt.title('original hist')

if __name__ == '__main__':

    filters = build_filters()

getGabor('D:\img.jpg',filters)



实验结果
LBP的方法展示，原始图像有三张，分别为camera、模板、蜂窝，结果展示了三种图像在LBP提取纹理方法下的直方图。