На первом изображении неправильно получено значение, и даже десятичная точка также не распознается. На втором изображении значения поступают, но десятичные дроби не распознаются. Просьба разобраться в вопросе и помочь мне в этом?
import numpy as np
import pytesseract
import argparse
import imutils
import cv2
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
image = 'D:/OCR/DigMeter2.jpg'
gray = cv2.imread(image, cv2.IMREAD_GRAYSCALE) # Read input image as Grayscale
cv2.imshow("gray", gray)
cv2.waitKey(1000)
# Erode the image
erd = cv2.erode(gray, None, iterations=2)
cv2.imshow("erd", erd)
cv2.waitKey(1000)
# threshold the image using Otsu's thresholding method# Convert to binary using automatic threshold (use cv2.THRESH_OTSU)
thresh = cv2.threshold(gray, 0, 255,cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
cv2.imshow("Otsu", thresh)
cv2.waitKey(1000)
# Dilate thresh for uniting text areas into blocks of rows.
dilated_thresh = cv2.dilate(thresh, np.ones((3,100)))
# Find contours on dilated_thresh
cnts = cv2.findContours(dilated_thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)[-2] # Use index [-2] to be compatible to OpenCV 3 and 4
# Build a list of bounding boxes
bounding_boxes = [cv2.boundingRect(c) for c in cnts]
# Sort bounding boxes from "top to bottom"
bounding_boxes = sorted(bounding_boxes, key=lambda b: b[1])
# Iterate bounding boxes
for b in bounding_boxes:
x, y, w, h = b
if (h > 10) and (w > 10):
# Crop a slice, and inverse black and white (tesseract prefers black text).
slice = 255 - thresh[max(y-10, 0):min(y+h+10, thresh.shape[0]), max(x-10, 0):min(x+w+10, thresh.shape[1])]
cv2.imshow("slice", slice)
cv2.waitKey(1000)
text = pytesseract.image_to_string(slice, config="-c tessedit"
"_char_whitelist=abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890-:."
" --psm 6"
" ")
text1 = pytesseract.image_to_string(image, lang='7seg', config='--psm 6 --oem 3 -c tessedit_char_whitelist=abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ12345678900123456789.')
text2 = pytesseract.image_to_string(slice, lang="letsgodigital", config="--psm 6 -c tessedit_char_whitelist=abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ12345678900123456789.")
print("[text] {}".format(text))
print("[text1] {}".format(text1))
print("[text2] {}".format(text2))
Подробнее здесь: https://stackoverflow.com/questions/781 ... -using-som
