Conda

You can use the channel simonflueckiger to install from Conda:

> conda install -c simonflueckiger tesserocr

or to get tesserocr compiled with tesseract 4.0.0:

> conda install -c simonflueckiger/label/tesseract-4.0.0-master tesserocr

pip

Download the wheel file corresponding to your Windows platform and Python installation from simonflueckiger/tesserocr-windows_build/releases and install them via:

> pip install <package_name>.whl

GetComponentImages example:

from PIL import Image
from tesserocr import PyTessBaseAPI, RIL

image = Image.open('/usr/src/tesseract/testing/phototest.tif')
with PyTessBaseAPI() as api:
    api.SetImage(image)
    boxes = api.GetComponentImages(RIL.TEXTLINE, True)
    print('Found {} textline image components.'.format(len(boxes)))
    for i, (im, box, _, _) in enumerate(boxes):
        # im is a PIL image object
        # box is a dict with x, y, w and h keys
        api.SetRectangle(box['x'], box['y'], box['w'], box['h'])
        ocrResult = api.GetUTF8Text()
        conf = api.MeanTextConf()
        print(u"Box[{0}]: x={x}, y={y}, w={w}, h={h}, "
              "confidence: {1}, text: {2}".format(i, conf, ocrResult, **box))

Orientation and script detection (OSD):

from PIL import Image
from tesserocr import PyTessBaseAPI, PSM

with PyTessBaseAPI(psm=PSM.AUTO_OSD) as api:
    image = Image.open("/usr/src/tesseract/testing/eurotext.tif")
    api.SetImage(image)
    api.Recognize()

    it = api.AnalyseLayout()
    orientation, direction, order, deskew_angle = it.Orientation()
    print("Orientation: {:d}".format(orientation))
    print("WritingDirection: {:d}".format(direction))
    print("TextlineOrder: {:d}".format(order))
    print("Deskew angle: {:.4f}".format(deskew_angle))

or more simply with OSD_ONLY page segmentation mode:

from tesserocr import PyTessBaseAPI, PSM

with PyTessBaseAPI(psm=PSM.OSD_ONLY) as api:
    api.SetImageFile("/usr/src/tesseract/testing/eurotext.tif")

    os = api.DetectOS()
    print("Orientation: {orientation}\nOrientation confidence: {oconfidence}\n"
          "Script: {script}\nScript confidence: {sconfidence}".format(**os))

more human-readable info with tesseract 4+ (demonstrates LSTM engine usage):

from tesserocr import PyTessBaseAPI, PSM, OEM

with PyTessBaseAPI(psm=PSM.OSD_ONLY, oem=OEM.LSTM_ONLY) as api:
    api.SetImageFile("/usr/src/tesseract/testing/eurotext.tif")

    os = api.DetectOrientationScript()
    print("Orientation: {orient_deg}\nOrientation confidence: {orient_conf}\n"
          "Script: {script_name}\nScript confidence: {script_conf}".format(**os))

Iterator over the classifier choices for a single symbol:

from __future__ import print_function

from tesserocr import PyTessBaseAPI, RIL, iterate_level

with PyTessBaseAPI() as api:
    api.SetImageFile('/usr/src/tesseract/testing/phototest.tif')
    api.SetVariable("save_blob_choices", "T")
    api.SetRectangle(37, 228, 548, 31)
    api.Recognize()

    ri = api.GetIterator()
    level = RIL.SYMBOL
    for r in iterate_level(ri, level):
        symbol = r.GetUTF8Text(level)  # r == ri
        conf = r.Confidence(level)
        if symbol:
            print(u'symbol {}, conf: {}'.format(symbol, conf), end='')
        indent = False
        ci = r.GetChoiceIterator()
        for c in ci:
            if indent:
                print('\t\t ', end='')
            print('\t- ', end='')
            choice = c.GetUTF8Text()  # c == ci
            print(u'{} conf: {}'.format(choice, c.Confidence()))
            indent = True
        print('---------------------------------------------')