[DeepLearning]Optical Character Recognition

import pytesseract
from PIL import Image, ImageEnhance, ImageFilter

# 指定Tesseract的路径（根据实际情况修改）
# pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'

# 加载并预处理图像
image = Image.open('path/to/your/image.jpg')
image = image.convert('L')  # 转换为灰度图
enhancer = ImageEnhance.Contrast(image)
image = enhancer.enhance(2)  # 提高对比度
image = image.filter(ImageFilter.MedianFilter())  # 应用中值滤波去噪
image = image.point(lambda x: 0 if x < 140 else 255)  # 二值化

# 使用Tesseract进行中文文本识别
text = pytesseract.image_to_string(image, lang='chi_sim')  # 使用简体中文数据

# 打印识别结果
print(text)

import cv2 as cv
import numpy as np
from matplotlib import pyplot as plt
 
img = cv.imread('sudoku.png', cv.IMREAD_GRAYSCALE)
assert img is not None, "file could not be read, check with os.path.exists()"
img = cv.medianBlur(img,5)
 
ret,th1 = cv.threshold(img,127,255,cv.THRESH_BINARY)
th2 = cv.adaptiveThreshold(img,255,cv.ADAPTIVE_THRESH_MEAN_C,\
            cv.THRESH_BINARY,11,2)
th3 = cv.adaptiveThreshold(img,255,cv.ADAPTIVE_THRESH_GAUSSIAN_C,\
            cv.THRESH_BINARY,11,2)
 
titles = ['Original Image', 'Global Thresholding (v = 127)',
            'Adaptive Mean Thresholding', 'Adaptive Gaussian Thresholding']
images = [img, th1, th2, th3]
 
for i in range(4):
    plt.subplot(2,2,i+1),plt.imshow(images[i],'gray')
    plt.title(titles[i])
    plt.xticks([]),plt.yticks([])
plt.show()