def image_from_archive(archive, name):
"""
Load image PGM file from tar archive.
Used for tarfile loading and unit test.
"""
member = archive.getmember(name)
filedata = archive.extractfile(member).read()
imagefiledata = cv.CreateMat(1, len(filedata), cv.CV_8UC1)
cv.SetData(imagefiledata, filedata, len(filedata))
return cv.DecodeImageM(imagefiledata)
def get_sample(self, filename, iscolor=cv.CV_LOAD_IMAGE_COLOR):
if not filename in self.image_cache:
filedata = None
if OpenCVTests.repoPath is not None:
candidate = OpenCVTests.repoPath + '/' + filename
if os.path.isfile(candidate):
with open(candidate, 'rb') as f:
filedata = f.read()
if filedata is None:
filedata = urllib.urlopen(OpenCVTests.repoUrl + '/' +
filename).read()
imagefiledata = cv.CreateMatHeader(1, len(filedata), cv.CV_8UC1)
cv.SetData(imagefiledata, filedata, len(filedata))
self.image_cache[filename] = cv.DecodeImageM(
imagefiledata, iscolor)
return self.image_cache[filename]
if __name__ == "__main__":
cv.NamedWindow("win")
if len(sys.argv) > 1:
filename = sys.argv[1]
im = cv.LoadImage(filename, cv.CV_LOAD_IMAGE_GRAYSCALE)
im3 = cv.LoadImage(filename, cv.CV_LOAD_IMAGE_COLOR)
else:
try: # try opening local copy of image
fileName = '../cpp/left01.jpg'
im = cv.LoadImageM(fileName, False)
im3 = cv.LoadImageM(fileName, True)
except: # if local copy cannot be opened, try downloading it
url = 'https://raw.github.com/opencv/opencv/master/samples/cpp/left01.jpg'
filedata = urllib2.urlopen(url).read()
imagefiledata = cv.CreateMatHeader(1, len(filedata), cv.CV_8UC1)
cv.SetData(imagefiledata, filedata, len(filedata))
im = cv.DecodeImageM(imagefiledata, cv.CV_LOAD_IMAGE_GRAYSCALE)
im3 = cv.DecodeImageM(imagefiledata, cv.CV_LOAD_IMAGE_COLOR)
chessboard_dim = (9, 6)
found_all, corners = cv.FindChessboardCorners(im, chessboard_dim)
print found_all, len(corners)
cv.DrawChessboardCorners(im3, chessboard_dim, corners, found_all)
cv.ShowImage("win", im3)
cv.WaitKey()
cv.DestroyAllWindows()
cv.ShowImage("image", self.dst_image)
cv.CalcArrHist([self.dst_image], self.hist)
(min_value, max_value, _, _) = cv.GetMinMaxHistValue(self.hist)
cv.Scale(self.hist.bins, self.hist.bins, float(self.hist_image.height) / max_value, 0)
cv.Set(self.hist_image, cv.ScalarAll(255))
bin_w = round(float(self.hist_image.width) / hist_size)
for i in range(hist_size):
cv.Rectangle(self.hist_image, (int(i * bin_w), self.hist_image.height),
(int((i + 1) * bin_w), self.hist_image.height - cv.Round(self.hist.bins[i])),
cv.ScalarAll(0), -1, 8, 0)
cv.ShowImage("histogram", self.hist_image)
if __name__ == "__main__":
# Load the source image.
if len(sys.argv) > 1:
src_image = cv.GetMat(cv.LoadImage(sys.argv[1], 0))
else:
url = 'https://code.ros.org/svn/opencv/trunk/opencv/samples/c/baboon.jpg'
filedata = urllib2.urlopen(url).read()
imagefiledata = cv.CreateMatHeader(1, len(filedata), cv.CV_8UC1)
cv.SetData(imagefiledata, filedata, len(filedata))
src_image = cv.DecodeImageM(imagefiledata, 0)
dh = DemHist(src_image)
cv.WaitKey(0)
def extract_features(filename, is_url=False):
'''Extracts features to be used in text image classifier.
:param filename: input image
:param is_url: is input image a url or a file path on disk
:return: tuple of features:
(average_slope, median_slope, average_tilt, median_tilt, median_differences, average_differences, nr_straight_lines)
Most relevant ones are average_slope, average_differences and nr_straight_lines.
'''
if is_url:
filedata = urllib2.urlopen(filename).read()
imagefiledata = cv.CreateMatHeader(1, len(filedata), cv.CV_8UC1)
cv.SetData(imagefiledata, filedata, len(filedata))
src = cv.DecodeImageM(imagefiledata, cv.CV_LOAD_IMAGE_GRAYSCALE)
else:
src = cv.LoadImage(filename, cv.CV_LOAD_IMAGE_GRAYSCALE)
# normalize size
normalized_size = 400
# smaller dimension will be 400, longer dimension will be proportional
orig_size = cv.GetSize(src)
max_dim_idx = max(enumerate(orig_size), key=lambda l: l[1])[0]
min_dim_idx = [idx for idx in [0, 1] if idx != max_dim_idx][0]
new_size = [0, 0]
new_size[min_dim_idx] = normalized_size
new_size[max_dim_idx] = int(
float(orig_size[max_dim_idx]) / orig_size[min_dim_idx] *
normalized_size)
dst = cv.CreateImage(new_size, 8, 1)
cv.Resize(src, dst)
# cv.SaveImage("/tmp/resized.jpg",dst)
src = dst
dst = cv.CreateImage(cv.GetSize(src), 8, 1)
color_dst = cv.CreateImage(cv.GetSize(src), 8, 3)
storage = cv.CreateMemStorage(0)
cv.Canny(src, dst, 50, 200, 3)
cv.CvtColor(dst, color_dst, cv.CV_GRAY2BGR)
slopes = []
# difference between xs or ys - variant of slope
tilts = []
# x coordinates of horizontal lines
horizontals = []
# y coordinates of vertical lines
verticals = []
if USE_STANDARD:
coords = cv.HoughLines2(dst, storage, cv.CV_HOUGH_STANDARD, 1,
pi / 180, 50, 50, 10)
lines = []
for coord in coords:
(rho, theta) = coord
a = cos(theta)
b = sin(theta)
x0 = a * rho
y0 = b * rho
pt1 = (cv.Round(x0 + 1000 * (-b)), cv.Round(y0 + 1000 * (a)))
pt2 = (cv.Round(x0 - 1000 * (-b)), cv.Round(y0 - 1000 * (a)))
lines += [(pt1, pt2)]
else:
lines = cv.HoughLines2(dst, storage, cv.CV_HOUGH_PROBABILISTIC, 1,
pi / 180, 50, 50, 10)
# eliminate duplicates - there are many especially with the standard version
# first round the coordinates to integers divisible with 5 (to eliminate different but really close ones)
# TODO
# lines = list(set(map(lambda l: tuple([int(p) - int(p)%5 for p in l]), lines)))
nr_straight_lines = 0
for line in lines:
(pt1, pt2) = line
# compute slope, rotate the line so that the slope is smallest
# (slope is either delta x/ delta y or the reverse)
# add smoothing term in denominator in case of 0
slope = min(
abs(pt1[1] - pt2[1]),
(abs(pt1[0] - pt2[0]))) / (max(abs(pt1[1] - pt2[1]),
(abs(pt1[0] - pt2[0]))) + 0.01)
# if slope < 0.1:
# if slope < 5:
if slope < 0.05:
if abs(pt1[0] - pt2[0]) < abs(pt1[1] - pt2[1]):
# means it's a horizontal line
horizontals.append(pt1[0])
else:
verticals.append(pt1[1])
if slope < 0.05:
# if slope < 5:
# if slope < 0.1:
nr_straight_lines += 1
slopes.append(slope)
tilts.append(min(abs(pt1[1] - pt2[1]), (abs(pt1[0] - pt2[0]))))
# print slope
average_slope = sum(slopes) / float(len(slopes))
median_slope = npmedian(nparray(slopes))
average_tilt = sum(tilts) / float(len(tilts))
median_tilt = npmedian(nparray(tilts))
differences = []
horizontals = sorted(horizontals)
verticals = sorted(verticals)
print "x_differences:"
for (i, x) in enumerate(horizontals):
if i > 0:
# print abs(horizontals[i] - horizontals[i-1])
differences.append(abs(horizontals[i] - horizontals[i - 1]))
print "y_differences:"
for (i, y) in enumerate(verticals):
if i > 0:
# print abs(verticals[i] - verticals[i-1])
differences.append(abs(verticals[i] - verticals[i - 1]))
print filename
print "average_slope:", average_slope
print "median_slope:", median_slope
print "average_tilt:", average_tilt
print "median_tilt:", median_tilt
median_differences = npmedian(nparray(differences))
print "median_differences:", median_differences
if not differences:
# big random number for average difference
average_differences = 50
else:
average_differences = sum(differences) / float(len(differences))
print "average_differences:", average_differences
print "nr_lines:", nr_straight_lines
# print "sorted xs:", sorted(lines)
return (average_slope, median_slope, average_tilt, median_tilt,
median_differences, average_differences, nr_straight_lines)
import cv2.cv as cv
import urllib2
# toggle between CV_HOUGH_STANDARD and CV_HOUGH_PROBILISTIC
USE_STANDARD = True
if __name__ == "__main__":
if len(sys.argv) > 1:
filename = sys.argv[1]
src = cv.LoadImage(filename, cv.CV_LOAD_IMAGE_GRAYSCALE)
else:
url = 'http://code.opencv.org/svn/opencv/trunk/opencv/doc/pics/building.jpg'
filedata = urllib2.urlopen(url).read()
imagefiledata = cv.CreateMatHeader(1, len(filedata), cv.CV_8UC1)
cv.SetData(imagefiledata, filedata, len(filedata))
src = cv.DecodeImageM(imagefiledata, cv.CV_LOAD_IMAGE_GRAYSCALE)
cv.NamedWindow("Source", 1)
cv.NamedWindow("Hough", 1)
while True:
dst = cv.CreateImage(cv.GetSize(src), 8, 1)
color_dst = cv.CreateImage(cv.GetSize(src), 8, 3)
storage = cv.CreateMemStorage(0)
lines = 0
cv.Canny(src, dst, 50, 200, 3)
cv.CvtColor(dst, color_dst, cv.CV_GRAY2BGR)
if USE_STANDARD:
lines = cv.HoughLines2(dst, storage, cv.CV_HOUGH_STANDARD, 1,
pi / 180, 100, 0, 0)
def lin2srgb(x):
a = 0.055
return numpy.where(x <= 0.0031308, x * 12.92,
(1 + a) * numpy.power(x, 1 / 2.4) - a)
if __name__ == "__main__":
if len(sys.argv) > 1:
img0 = cv.LoadImageM(sys.argv[1], cv.CV_LOAD_IMAGE_COLOR)
else:
url = 'http://code.opencv.org/svn/opencv/trunk/opencv/samples/c/lena.jpg'
filedata = urllib2.urlopen(url).read()
imagefiledata = cv.CreateMatHeader(1, len(filedata), cv.CV_8UC1)
cv.SetData(imagefiledata, filedata, len(filedata))
img0 = cv.DecodeImageM(imagefiledata, cv.CV_LOAD_IMAGE_COLOR)
cv.NamedWindow("original", 1)
cv.ShowImage("original", img0)
# Image was originally bytes in range 0-255. Turn it into an array of floats in range 0.0 - 1.0
n = numpy.asarray(img0) / 255.0
# Use NumPy to do some transformations on the image
# Negate the image by subtracting it from 1.0
cv.NamedWindow("negative")
cv.ShowImage("negative", cv.fromarray(1.0 - n))
# Assume the image was sRGB, and compute the linear version.
cv.NamedWindow("linear")
