Question

我想检测图像中每个角色的位置。

我按照how to get character position in pytesseract的建议尝试了pytesseract但是给了我一个错误

import csv
import cv2
from pytesseract import pytesseract as pt

pt.run_tesseract('bw.png', 'output', lang=None, boxes=True, config="hocr")

# To read the coordinates
boxes = []
with open('output.box', 'rb') as f:
    reader = csv.reader(f, delimiter = ' ')
    for row in reader:
        if(len(row)==6):
            boxes.append(row)

# Draw the bounding box
img = cv2.imread('bw.png')
h, w, _ = img.shape
for b in boxes:
    img = cv2.rectangle(img,(int(b[1]),h-int(b[2])),(int(b[3]),h-int(b[4])),(255,0,0),2)

cv2.imshow('output',img)



---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-38-bad5c94b3e13> in <module>()
      3 from pytesseract import pytesseract as pt
      4 
----> 5 pt.run_tesseract('input/1230.jpg', 'output', lang=None, boxes=True, config="hocr")
      6 
      7 # To read the coordinates

TypeError: run_tesseract() got an unexpected keyword argument 'boxes'

我确实意识到它对于python 2.7，有人可以指导我或者给我一个如何为python 3.x做一个开始

然后我尝试了tesserocr似乎无法解决tessdata的路径无论如何，我尝试使用tesseracct-ocr，尝试手动下载tessdata但仍然是同样的错误。

from PIL import Image
from tesserocr import PyTessBaseAPI, RIL

image = Image.open('train/1230.jpg')
with PyTessBaseAPI(path="C:\\Users\light\Desktop\tessdata-master") 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)


---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-11-68789b2bbe93> in <module>()
      3 
      4 image = Image.open('train/1230.jpg')
----> 5 with PyTessBaseAPI(path="C:\\Users\light\Desktop\tessdata-master") as api:
      6     api.SetImage(image)
      7     boxes = api.GetComponentImages(RIL.TEXTLINE, True)

tesserocr.pyx in tesserocr._tesserocr.PyTessBaseAPI.__cinit__()

tesserocr.pyx in tesserocr._tesserocr.PyTessBaseAPI._init_api()

RuntimeError: Failed to init API, possibly an invalid tessdata path: C:\Users\light\Desktop essdata-master

Answer 1

boxes参数仅对pytesseract版本0.1.x有效。它已在0.2.0版本中删除。

Answer 2

使用方法image_to_boxes使用pytesseract获取图像中的字符及其位置：

ret = pt.image_to_boxes(pil_img)

结果是一个字符串，其中每一行都是一个字符，它的位置（x1，y1，X2，y2）用空格分隔：

a 30 10 45 20
b 49 12 54 23

如何使用python 3.x检测字符的位置

2 个答案: