当前位置：首页 > news >正文

文本字符分割算法尝试

news 2025/7/13 3:46:06

一、基于opencv的分割算法

import cv2
import numpy as np
from matplotlib import pyplot as pltimg = cv2.imread('scratch.png', 0)
# global thresholding
ret1, th1 = cv2.threshold(img, 127, 255, cv2.THRESH_BINARY)
# Otsu's thresholding
th2 = cv2.adaptiveThreshold(img, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 11, 2)
# Otsu's thresholding
# 阈值一定要设为 0 !
ret3, th3 = cv2.threshold(img, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
# plot all the images and their histograms
images = [img, 0, th1, img, 0, th2, img, 0, th3]
titles = ['Original Noisy Image', 'Histogram', 'Global Thresholding (v=127)','Original Noisy Image', 'Histogram', "Adaptive Thresholding",'Original Noisy Image', 'Histogram', "Otsu's Thresholding"
]
# 这里使用了 pyplot 中画直方图的方法, plt.hist, 要注意的是它的参数是一维数组
# 所以这里使用了( numpy ) ravel 方法,将多维数组转换成一维,也可以使用 flatten 方法
# ndarray.flat 1-D iterator over an array.
# ndarray.flatten 1-D array copy of the elements of an array in row-major order.
for i in range(3):plt.subplot(3, 3, i * 3 + 1), plt.imshow(images[i * 3], 'gray')plt.title(titles[i * 3]), plt.xticks([]), plt.yticks([])plt.subplot(3, 3, i * 3 + 2), plt.hist(images[i * 3].ravel(), 256)plt.title(titles[i * 3 + 1]), plt.xticks([]), plt.yticks([])plt.subplot(3, 3, i * 3 + 3), plt.imshow(images[i * 3 + 2], 'gray')plt.title(titles[i * 3 + 2]), plt.xticks([]), plt.yticks([])
plt.show()

二、基于skimage的分割算法尝试

参考链接：

Niblack and Sauvola Thresholding — skimage 0.24.1rc0.dev0 documentation (scikit-image.org)

Python图像处理二值化方法实例汇总_python_脚本之家 (jb51.net)

skimage sauvola阈值 (主要用于文本检测)

import matplotlib
import matplotlib.pyplot as pltfrom skimage.data import page
from skimage.filters import (threshold_otsu, threshold_niblack,threshold_sauvola)matplotlib.rcParams['font.size'] = 9image = page()
binary_global = image > threshold_otsu(image)window_size = 25
thresh_niblack = threshold_niblack(image, window_size=window_size, k=0.8)
thresh_sauvola = threshold_sauvola(image, window_size=window_size)binary_niblack = image > thresh_niblack
binary_sauvola = image > thresh_sauvolaplt.figure(figsize=(8, 7))
plt.subplot(2, 2, 1)
plt.imshow(image, cmap=plt.cm.gray)
plt.title('Original')
plt.axis('off')plt.subplot(2, 2, 2)
plt.title('Global Threshold')
plt.imshow(binary_global, cmap=plt.cm.gray)
plt.axis('off')plt.subplot(2, 2, 3)
plt.imshow(binary_niblack, cmap=plt.cm.gray)
plt.title('Niblack Threshold')
plt.axis('off')plt.subplot(2, 2, 4)
plt.imshow(binary_sauvola, cmap=plt.cm.gray)
plt.title('Sauvola Threshold')
plt.axis('off')plt.show()