序列图像分割-文字识别-导入表格

任务：将以下三张图片中左上角的数字导入表格中

001.jpg

002.jpg

003.jpg

1.为了更好的识别，我们首先要把我们需要的区域提取出来，提取结果如下



2.OCR识别，导入表格

具体代码如下：

from PIL import Image
import pytesseract
import os
import xlsxwriter


path = "D:/yuantu/"   # 图像读取地址
savepath = "D:/picture/"  # 图像保存地址
filelist = os.listdir(path)  # 打开对应的文件夹
total_num = len(filelist)  # 得到文件夹中图像的个数

workbook = xlsxwriter.Workbook('D:/outcome.xlsx') #存放表格
worksheet = workbook.add_worksheet()
x = 0
y = 0
for i in range(total_num):
    jpg_name = path + '00' +str(i+1) + '.jpg' # 图像的读取地址
    img = Image.open(jpg_name)
    def cropimg():
         region = img.crop((0, 0, 200, 200))  ## 裁剪
         result_img = region
         savejpg_name = savepath + str(i) + '.jpg'
         result_img.save(savejpg_name)
         text = pytesseract.image_to_string(Image.open(savejpg_name), lang="eng") # 文本识别
         worksheet.write(x, y, i+1)
         worksheet.write(x, y+1, text)

    cropimg()
    x=x+1

workbook.close()