均值二值化，59维

bj21002000

已于 2024-02-18 14:32:11 修改

阅读量404

点赞数

文章标签： python

于 2023-04-11 11:46:10 首次发布

本文链接：https://blog.csdn.net/bj21002000/article/details/130080316

版权

该代码实现了从灰度图像中提取MeanLocalBinaryPattern(MeanLBP)特征，使用OpenCV库进行颜色空间转换，然后计算每个像素点周围的LBP值，最后统计不同LBP值的频率作为特征向量。

摘要由CSDN通过智能技术生成

import cv2
import numpy as np
############################################################
def mean_local_binary_pattern(image, radius, n_points):
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
lbp = np.zeros_like(gray)
for i in range(radius,gray.shape[0]-radius):
for j in range(radius,gray.shape[1]-radius):
center = gray[i,j]
values = []
for r in range(-radius,radius+1):
for c in range(-radius,radius+1):
if r0 and c0:
continue
px = gray[i+r, j+c]
values.append(1 if px>=center else 0)
lbp[i,j] = int(sum(values)/len(values)*(n_points-1))
hist, _ = np.histogram(lbp.ravel(), bins=np.arange(n_points+1), range=(0,n_points))
return hist.astype(“float”)
############################################################
image = cv2.imread(‘all_souls_000000.jpg’)
feature_vector = mean_local_binary_pattern(image, radius=3, n_points=59)
print(feature_vector)