f4334277
 Hu Chunming
提交3rdparty
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
|
'''
Text detection model: https://github.com/argman/EAST
Download link: https://www.dropbox.com/s/r2ingd0l3zt8hxs/frozen_east_text_detection.tar.gz?dl=1
CRNN Text recognition model taken from here: https://github.com/meijieru/crnn.pytorch
How to convert from pb to onnx:
Using classes from here: https://github.com/meijieru/crnn.pytorch/blob/master/models/crnn.py
More converted onnx text recognition models can be downloaded directly here:
Download link: https://drive.google.com/drive/folders/1cTbQ3nuZG-EKWak6emD_s8_hHXWz7lAr?usp=sharing
And these models taken from here:https://github.com/clovaai/deep-text-recognition-benchmark
import torch
from models.crnn import CRNN
model = CRNN(32, 1, 37, 256)
model.load_state_dict(torch.load('crnn.pth'))
dummy_input = torch.randn(1, 1, 32, 100)
torch.onnx.export(model, dummy_input, "crnn.onnx", verbose=True)
'''
# Import required modules
import numpy as np
import cv2 as cv
import math
import argparse
############ Add argument parser for command line arguments ############
parser = argparse.ArgumentParser(
description="Use this script to run TensorFlow implementation (https://github.com/argman/EAST) of "
"EAST: An Efficient and Accurate Scene Text Detector (https://arxiv.org/abs/1704.03155v2)"
"The OCR model can be obtained from converting the pretrained CRNN model to .onnx format from the github repository https://github.com/meijieru/crnn.pytorch"
"Or you can download trained OCR model directly from https://drive.google.com/drive/folders/1cTbQ3nuZG-EKWak6emD_s8_hHXWz7lAr?usp=sharing")
parser.add_argument('--input',
help='Path to input image or video file. Skip this argument to capture frames from a camera.')
parser.add_argument('--model', '-m', required=True,
help='Path to a binary .pb file contains trained detector network.')
parser.add_argument('--ocr', default="crnn.onnx",
help="Path to a binary .pb or .onnx file contains trained recognition network", )
parser.add_argument('--width', type=int, default=320,
help='Preprocess input image by resizing to a specific width. It should be multiple by 32.')
parser.add_argument('--height', type=int, default=320,
help='Preprocess input image by resizing to a specific height. It should be multiple by 32.')
parser.add_argument('--thr', type=float, default=0.5,
help='Confidence threshold.')
parser.add_argument('--nms', type=float, default=0.4,
help='Non-maximum suppression threshold.')
args = parser.parse_args()
############ Utility functions ############
def fourPointsTransform(frame, vertices):
vertices = np.asarray(vertices)
outputSize = (100, 32)
targetVertices = np.array([
[0, outputSize[1] - 1],
[0, 0],
[outputSize[0] - 1, 0],
[outputSize[0] - 1, outputSize[1] - 1]], dtype="float32")
rotationMatrix = cv.getPerspectiveTransform(vertices, targetVertices)
result = cv.warpPerspective(frame, rotationMatrix, outputSize)
return result
def decodeText(scores):
text = ""
alphabet = "0123456789abcdefghijklmnopqrstuvwxyz"
for i in range(scores.shape[0]):
c = np.argmax(scores[i][0])
if c != 0:
text += alphabet[c - 1]
else:
text += '-'
# adjacent same letters as well as background text must be removed to get the final output
char_list = []
for i in range(len(text)):
if text[i] != '-' and (not (i > 0 and text[i] == text[i - 1])):
char_list.append(text[i])
return ''.join(char_list)
def decodeBoundingBoxes(scores, geometry, scoreThresh):
detections = []
confidences = []
############ CHECK DIMENSIONS AND SHAPES OF geometry AND scores ############
assert len(scores.shape) == 4, "Incorrect dimensions of scores"
assert len(geometry.shape) == 4, "Incorrect dimensions of geometry"
assert scores.shape[0] == 1, "Invalid dimensions of scores"
assert geometry.shape[0] == 1, "Invalid dimensions of geometry"
assert scores.shape[1] == 1, "Invalid dimensions of scores"
assert geometry.shape[1] == 5, "Invalid dimensions of geometry"
assert scores.shape[2] == geometry.shape[2], "Invalid dimensions of scores and geometry"
assert scores.shape[3] == geometry.shape[3], "Invalid dimensions of scores and geometry"
height = scores.shape[2]
width = scores.shape[3]
for y in range(0, height):
# Extract data from scores
scoresData = scores[0][0][y]
x0_data = geometry[0][0][y]
x1_data = geometry[0][1][y]
x2_data = geometry[0][2][y]
x3_data = geometry[0][3][y]
anglesData = geometry[0][4][y]
for x in range(0, width):
score = scoresData[x]
# If score is lower than threshold score, move to next x
if (score < scoreThresh):
continue
# Calculate offset
offsetX = x * 4.0
offsetY = y * 4.0
angle = anglesData[x]
# Calculate cos and sin of angle
cosA = math.cos(angle)
sinA = math.sin(angle)
h = x0_data[x] + x2_data[x]
w = x1_data[x] + x3_data[x]
# Calculate offset
offset = ([offsetX + cosA * x1_data[x] + sinA * x2_data[x], offsetY - sinA * x1_data[x] + cosA * x2_data[x]])
# Find points for rectangle
p1 = (-sinA * h + offset[0], -cosA * h + offset[1])
p3 = (-cosA * w + offset[0], sinA * w + offset[1])
center = (0.5 * (p1[0] + p3[0]), 0.5 * (p1[1] + p3[1]))
detections.append((center, (w, h), -1 * angle * 180.0 / math.pi))
confidences.append(float(score))
# Return detections and confidences
return [detections, confidences]
def main():
# Read and store arguments
confThreshold = args.thr
nmsThreshold = args.nms
inpWidth = args.width
inpHeight = args.height
modelDetector = args.model
modelRecognition = args.ocr
# Load network
detector = cv.dnn.readNet(modelDetector)
recognizer = cv.dnn.readNet(modelRecognition)
# Create a new named window
kWinName = "EAST: An Efficient and Accurate Scene Text Detector"
cv.namedWindow(kWinName, cv.WINDOW_NORMAL)
outNames = []
outNames.append("feature_fusion/Conv_7/Sigmoid")
outNames.append("feature_fusion/concat_3")
# Open a video file or an image file or a camera stream
cap = cv.VideoCapture(args.input if args.input else 0)
tickmeter = cv.TickMeter()
while cv.waitKey(1) < 0:
# Read frame
hasFrame, frame = cap.read()
if not hasFrame:
cv.waitKey()
break
# Get frame height and width
height_ = frame.shape[0]
width_ = frame.shape[1]
rW = width_ / float(inpWidth)
rH = height_ / float(inpHeight)
# Create a 4D blob from frame.
blob = cv.dnn.blobFromImage(frame, 1.0, (inpWidth, inpHeight), (123.68, 116.78, 103.94), True, False)
# Run the detection model
detector.setInput(blob)
tickmeter.start()
outs = detector.forward(outNames)
tickmeter.stop()
# Get scores and geometry
scores = outs[0]
geometry = outs[1]
[boxes, confidences] = decodeBoundingBoxes(scores, geometry, confThreshold)
# Apply NMS
indices = cv.dnn.NMSBoxesRotated(boxes, confidences, confThreshold, nmsThreshold)
for i in indices:
# get 4 corners of the rotated rect
vertices = cv.boxPoints(boxes[i[0]])
# scale the bounding box coordinates based on the respective ratios
for j in range(4):
vertices[j][0] *= rW
vertices[j][1] *= rH
# get cropped image using perspective transform
if modelRecognition:
cropped = fourPointsTransform(frame, vertices)
cropped = cv.cvtColor(cropped, cv.COLOR_BGR2GRAY)
# Create a 4D blob from cropped image
blob = cv.dnn.blobFromImage(cropped, size=(100, 32), mean=127.5, scalefactor=1 / 127.5)
recognizer.setInput(blob)
# Run the recognition model
tickmeter.start()
result = recognizer.forward()
tickmeter.stop()
# decode the result into text
wordRecognized = decodeText(result)
cv.putText(frame, wordRecognized, (int(vertices[1][0]), int(vertices[1][1])), cv.FONT_HERSHEY_SIMPLEX,
0.5, (255, 0, 0))
for j in range(4):
p1 = (int(vertices[j][0]), int(vertices[j][1]))
p2 = (int(vertices[(j + 1) % 4][0]), int(vertices[(j + 1) % 4][1]))
cv.line(frame, p1, p2, (0, 255, 0), 1)
# Put efficiency information
label = 'Inference time: %.2f ms' % (tickmeter.getTimeMilli())
cv.putText(frame, label, (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0))
# Display the frame
cv.imshow(kWinName, frame)
tickmeter.reset()
if __name__ == "__main__":
main()
|
