一、pip install pytesseract

二、安装识别引擎tesseract-ocr

https://digi.bib.uni-mannheim.de/tesseract/

下载安装后，添加系统环境路径

python pytesseract psm 选项参数

Page segmentation modes:

0    Orientation and script detection (OSD) only.

1    Automatic page segmentation with OSD.

2    Automatic page segmentation, but no OSD, or OCR.

3    Fully automatic page segmentation, but no OSD. (Default)

4    Assume a single column of text of variable sizes.

5    Assume a single uniform block of vertically aligned text.

6    Assume a single uniform block of text.

7    Treat the image as a single text line.

8    Treat the image as a single word.

9    Treat the image as a single word in a circle.

10    Treat the image as a single character.

11    Sparse text. Find as much text as possible in no particular order.

12    Sparse text with OSD.

13    Raw line. Treat the image as a single text line,bypassing hacks that areTesseract-specific.

Here is a sample usage ofimage_to_stringwith multiple parameters.

target = pytesseract.image_to_string(image, lang='eng', boxes=False, \

config='--psm 10 --oem 3 -c tessedit_char_whitelist=0123456789')