136 lines
4.0 KiB
Python
136 lines
4.0 KiB
Python
try:
|
|
from PIL import Image
|
|
except ImportError:
|
|
import Image
|
|
from cv2 import cv2
|
|
import pytesseract
|
|
import argparse
|
|
import numpy as np
|
|
from imutils.object_detection import non_max_suppression
|
|
|
|
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
|
|
faceCascade = cv2.CascadeClassifier(
|
|
'haarcascade/haarcascade_frontalface_default.xml')
|
|
|
|
|
|
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]
|
|
rects = []
|
|
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] < 0.5:
|
|
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 both the starting and ending (x, y)-coordinates
|
|
# for the text prediction bounding box
|
|
endX = int(offsetX + (cos * xData1[x]) + (sin * xData2[x]))
|
|
endY = int(offsetY - (sin * xData1[x]) + (cos * xData2[x]))
|
|
startX = int(endX - w)
|
|
startY = int(endY - h)
|
|
|
|
# add the bounding box coordinates and probability score
|
|
# to our respective lists
|
|
rects.append((startX, startY, endX, endY))
|
|
confidences.append(scoresData[x])
|
|
|
|
# return a tuple of the bounding boxes and associated confidences
|
|
return (rects, confidences)
|
|
|
|
|
|
def findNumber(url):
|
|
image = cv2.imread(url)
|
|
orig = image.copy()
|
|
(origH, origW) = image.shape[:2]
|
|
(newW, newH) = (320,320)
|
|
rW = origW / float(newW)
|
|
rH = origH / float(newH)
|
|
image = cv2.resize(image, (newW, newH))
|
|
(H, W) = image.shape[:2]
|
|
layerNames = [
|
|
"feature_fusion/Conv_7/Sigmoid",
|
|
"feature_fusion/concat_3"]
|
|
net = cv2.dnn.readNet("../EAST/frozen_east_text_detection.pb")
|
|
blob = cv2.dnn.blobFromImage(image, 1.0, (W, H),
|
|
(123.68, 116.78, 103.94), swapRB=True, crop=False)
|
|
net.setInput(blob)
|
|
(scores, geometry) = net.forward(layerNames)
|
|
(rects, confidences) = decode_predictions(scores, geometry)
|
|
boxes = non_max_suppression(np.array(rects), probs=confidences)
|
|
results = []
|
|
for (startX, startY, endX, endY) in boxes:
|
|
|
|
startX = int(startX * rW)
|
|
startY = int(startY * rH)
|
|
endX = int(endX * rW)
|
|
endY = int(endY * rH)
|
|
|
|
dX = int((endX - startX) * 0.0)
|
|
dY = int((endY - startY) * 0.0)
|
|
|
|
startX = max(0, startX - dX)
|
|
startY = max(0, startY - dY)
|
|
endX = min(origW, endX + (dX * 2))
|
|
endY = min(origH, endY + (dY * 2))
|
|
|
|
roi = orig[startY:endY, startX:endX]
|
|
|
|
config = ("-l eng --oem 1 --psm 7")
|
|
text = pytesseract.image_to_string(roi, config=config)
|
|
|
|
results.append(((startX, startY, endX, endY), text))
|
|
|
|
results = sorted(results, key=lambda r: r[0][1])
|
|
wyniki = []
|
|
for ((startX, startY, endX, endY), text) in results:
|
|
if( text.isdigit() ):
|
|
wyniki.append(text)
|
|
# print("OCR TEXT")
|
|
# print("========")
|
|
# print("{}\n".format(text))
|
|
|
|
# text = "".join([c if ord(c) < 128 else "" for c in text]).strip()
|
|
# output = orig.copy()
|
|
# cv2.rectangle(output, (startX, startY), (endX, endY),
|
|
# (0, 0, 255), 2)
|
|
# cv2.putText(output, text, (startX, startY - 20),
|
|
# cv2.FONT_HERSHEY_SIMPLEX, 1.2, (0, 0, 255), 3)
|
|
|
|
# cv2.imshow("Text Detection", output)
|
|
# cv2.waitKey(0)
|
|
|
|
return wyniki
|