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
|
#!/usr/bin/python
import sys
import os
import cv2 as cv
import numpy as np
print('\ntextdetection.py')
print(' A demo script of the Extremal Region Filter algorithm described in:')
print(' Neumann L., Matas J.: Real-Time Scene Text Localization and Recognition, CVPR 2012\n')
if (len(sys.argv) < 2):
print(' (ERROR) You must call this script with an argument (path_to_image_to_be_processed)\n')
quit()
pathname = os.path.dirname(sys.argv[0])
img = cv.imread(str(sys.argv[1]))
# for visualization
vis = img.copy()
# Extract channels to be processed individually
channels = list(cv.text.computeNMChannels(img))
# Append negative channels to detect ER- (bright regions over dark background)
cn = len(channels)-1
for c in range(0,cn):
channels.append(255-channels[c])
# Apply the default cascade classifier to each independent channel (could be done in parallel)
erc1 = cv.text.loadClassifierNM1('trained_classifierNM1.xml')
er1 = cv.text.createERFilterNM1(erc1,16,0.00015,0.13,0.2,True,0.1)
erc2 = cv.text.loadClassifierNM2('trained_classifierNM2.xml')
er2 = cv.text.createERFilterNM2(erc2,0.5)
print("Extracting Class Specific Extremal Regions from "+str(len(channels))+" channels ...")
print(" (...) this may take a while (...)")
for channel in channels:
regions = cv.text.detectRegions(channel,er1,er2)
rects = cv.text.erGrouping(img,channel,[r.tolist() for r in regions])
#rects = cv.text.erGrouping(img,channel,[x.tolist() for x in regions], cv.text.ERGROUPING_ORIENTATION_ANY,'../../GSoC2014/opencv_contrib/modules/text/samples/trained_classifier_erGrouping.xml',0.5)
#Visualization
for rect in rects:
cv.rectangle(vis, (rect[0],rect[1]), (rect[0]+rect[2],rect[1]+rect[3]), (0, 0, 0), 2)
cv.rectangle(vis, (rect[0],rect[1]), (rect[0]+rect[2],rect[1]+rect[3]), (255, 255, 255), 1)
#Visualization
cv.imshow("Text detection result", vis)
cv.waitKey(0)
|
