exam-segment-django/segment/ocr/luo_ocr/sheetocr.py

'''
使用Tesseract 对试卷做OCR

Tesseract Usage:
  tesseract --help | --help-extra | --help-psm | --help-oem | --version
  tesseract --list-langs [--tessdata-dir PATH]
  tesseract --print-parameters [options...] [configfile...]
  tesseract imagename|imagelist|stdin outputbase|stdout [options...] [configfile...]

OCR options:
  --tessdata-dir PATH   Specify the location of tessdata path.
  --user-words PATH     Specify the location of user words file.
  --user-patterns PATH  Specify the location of user patterns file.
  -l LANG[+LANG]        Specify language(s) used for OCR.
  -c VAR=VALUE          Set value for config variables.
                        Multiple -c arguments are allowed.
  --psm NUM             Specify page segmentation mode.
  --oem NUM             Specify OCR Engine mode.
NOTE: These options must occur before any configfile.

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 are Tesseract-specific.

OCR Engine modes:
  0    Legacy engine only.
  1    Neural nets LSTM engine only.
  2    Legacy + LSTM engines.
  3    Default, based on what is available.

Single options:
  -h, --help            Show minimal help message.
  --help-extra          Show extra help for advanced users.
  --help-psm            Show page segmentation modes.
  --help-oem            Show OCR Engine modes.
  -v, --version         Show version information.
  --list-langs          List available languages for tesseract engine.
  --print-parameters    Print tesseract parameters.

'''
import os
import pytesseract


# ocr图片文件，生成文本文件，较好的参数为 -l chi_sim+eng --psm 6
def sheetocr(picture, output, lang, psm):
    cmd = 'tesseract' + ' ' + picture + ' ' + output + ' ' + lang + ' ' + psm
    os.system(cmd)


# ocr 图像，生成文本，较好的参数为'chi_sim+eng',  '--psm 6'
def sheetocr_py(img, lang, psm):
    words = pytesseract.image_to_string(img, lang=lang, config=psm)
    return words