Распознать текст с помощью tesseract

Question

Здравствуйте, я пытаюсь распознать текст из изображения, используя Tesseract, но не могу получить результат. Я использую технику EAST для обнаружения текста. У меня есть еще один вопрос, как я могу продлить отступ поля. cv2.putText в этом случае не работает. оригинальный код для обнаружения текста: https://github.com/opencv/opencv/blob/master/samples/dnn/text_detection.cpp

import cv2
import numpy as np
import argparse
import time
import math
import matplotlib.pyplot as plt
import skimage.io as io
import os
from imutils.object_detection import non_max_suppression
import pytesseract
print(np.__version__)

def decode_predictions(scores, geometry):
    **# grab the number of rows and columns from the scores volume, then
    # initialize our set of bounding box rectangles and corresponding
    # confidence scores**
    (numRows, numCols) = scores.shape[2:4]
    boxes = []
    confidences = []

    **# loop over the number of rows**
    for y in range(0, numRows):
        **# extract the scores (probabilities), followed by the geometrical
        # data used to derive potential bounding box coordinates that
        # surround text**
        scoresData = scores[0, 0, y]
        xData0 = geometry[0, 0, y]
        xData1 = geometry[0, 1, y]
        xData2 = geometry[0, 2, y]
        xData3 = geometry[0, 3, y]
        anglesData = geometry[0, 4, y]

        **# loop over the number of columns**
        for x in range(0, numCols):
            **# if our score does not have sufficient probability, ignore it**
            if scoresData[x] < args["min_confidence"]:
                continue

            **# compute the offset factor as our resulting feature maps will
            # be 4x smaller than the input image**
            (offsetX, offsetY) = (x * 4.0, y * 4.0)

            **# extract the rotation angle for the prediction and then
            # compute the sin and cosine**
            angle = anglesData[x]
            cos = np.cos(angle)
            sin = np.sin(angle)

            **# use the geometry volume to derive the width and height of
            # the bounding box**
            h = xData0[x] + xData2[x]
            w = xData1[x] + xData3[x]

            **# compute the rotated rect for
            # the text prediction bounding box**
            offset = (offsetX + (cos * xData1[x]) + (sin * xData2[x]), offsetY - (sin * xData1[x]) + (cos * xData2[x]))
            p1 = (-sin * h + offset[0], -cos * h + offset[1])
            p3 = (-cos * w + offset[0],  sin * w + offset[1])
            center = (0.5*(p1[0]+p3[0]), 0.5*(p1[1]+p3[1]))

            **# add the bounding box coordinates and probability score to
            # our respective lists**
            boxes.append((center, (w,h), -angle * 180.0 / math.pi))
            confidences.append(float(scoresData[x]))
    return (boxes, confidences)
args = {
    "image":"C:\\Users\\ckunwar\\Test_Images\\licence_plate1\\52.jpg",
    "east": "frozen_east_text_detection.pb",
    "min_confidence":0.25,
    "nms_thresh": 0.24,
    "width":480,
    "height":320,
    "padding":0.0
}

    **# load the input image and grab the image dimensions**
image = cv2.imread(args["image"])
orig = image.copy()
(H, W) = image.shape[:2]
#print(H,W)
**# set the new width and height and then determine the ratio in change
# for both the width and height**
(newW, newH) = (args["width"], args["height"])
rW = W / float(newW)
rH = H / float(newH)

**# resize the image and grab the new image dimensions**
image = cv2.resize(image, (newW, newH))
(H, W) = image.shape[:2]

**# define the two output layer names for the EAST detector model that
# we are interested -- the first is the output probabilities and the
# second can be used to derive the bounding box coordinates of text**
layerNames = ["feature_fusion/Conv_7/Sigmoid","feature_fusion/concat_3"]

**# load the pre-trained EAST text detector**
print("[INFO] loading EAST text detector...")
net = cv2.dnn.readNet(args["east"])

**# construct a blob from the image and then perform a forward pass of
# the model to obtain the two output layer sets**
blob = cv2.dnn.blobFromImage(image, 1.0, (W, H),(123.68, 116.78, 103.94), swapRB=True, crop=False)
start = time.time()
net.setInput(blob)
(scores, geometry) = net.forward(layerNames)
end = time.time()

**# show timing information on text prediction**
print("[INFO] text detection took {:.6f} seconds".format(end - start))

(boxes, confidences) = decode_predictions(scores, geometry)

**# apply non-maxima suppression to suppress weak, overlapping bounding boxes**
indices = cv2.dnn.NMSBoxesRotated(boxes, confidences, args["min_confidence"], args["nms_thresh"])

results = []


**# loop over the bounding boxes**
for i in indices:
  **# get 4 corners of the rotated rect**
  vertices = cv2.boxPoints(boxes[i[0]])

  **# scale the bounding box coordinates based on the respective ratios**
  for j in [0,1,2,3]:
    vertices[j][0] *= rW
    vertices[j][1] *= rH

  **# draw the bounding box on the image**
  for j in [0,1,2,3]:
    p1 = (vertices[j][0], vertices[j][1])
    p2 = (vertices[(j + 1) % 4][0], vertices[(j + 1) % 4][1])


    config = ("-l eng --oem 3 --psm 11")
    text = pytesseract.image_to_string(orig,config=config)

    results.append(((p1,p2), text))

results = sorted(results, key=lambda r:r[0][1])

output = orig.copy()

for ((p1,p2), text) in results:
    print("OCR TEXT")
    print("========")
    print("{}\n".format(text))

    text = "".join([c if ord(c) < 128 else "" for c in text]).strip()
    cv2.line(output, p1, p2, (0, 255, 0), 2)
    #cv2.rectangle(output, p1, p2,(0, 255, 0), 2)
    cv2.putText(output, text,cv2.FONT_HERSHEY_TRIPLEX, 0.8, (0, 0, 255), 2)



**# show the output image**
#orig = cv2.cvtColor(orig, cv2.COLOR_BGR2RGB)

cv2.imshow("Text Detection", output)
cv2.waitKey(0)