def main():
print __doc__
parser = argparse.ArgumentParser(description='Test image segmentation')
parser.add_argument('image', metavar='FILE', help='Input image')
parser.add_argument('--max-size', metavar='N', type=float, help="Scale the input image down if its perimeter exceeds N. Default is no scaling.")
args = parser.parse_args()
img = cv2.imread(args.image)
if img == None or img.size == 0:
sys.stderr.write("Failed to read %s\n" % args.image)
return -1
sys.stderr.write("Processing %s...\n" % args.image)
# Scale the image down if its perimeter exceeds the maximum (if set).
img = common.scale_max_perimeter(img, args.max_size)
# Linear enhancement
enhanced1 = ft.naik_murthy_linear(img)
# Nonlinear enhancement using S-type function
enhanced2a = ft.naik_murthy_nonlinear(enhanced1, ft.s_type_enhancement, 0, 3, 0.5, 2)
enhanced2b = ft.naik_murthy_nonlinear(enhanced1, ft.s_type_enhancement, 0, 3, 1.5, 2)
# Enhancement using histogram equalization
sums = bgr_to_sums(img) # Range 0..(255*3-1)
sums = cv2.normalize(sums, None, 0, 255, cv2.NORM_MINMAX) # Range 0..255
sums = cv2.equalizeHist(np.uint8(sums))
sums = cv2.normalize(np.float32(sums), None, 0, 3, cv2.NORM_MINMAX) # Range 0..3
enhanced3 = ft.naik_murthy_nonlinear(img, sums, fmap=True)
# Display the image in a window.
cv2.namedWindow('image')
cv2.imshow('image', img)
while True:
k = cv2.waitKey(0) & 0xFF
if k == ord('0'):
cv2.imshow('image', img)
elif k == ord('1'):
cv2.imshow('image', enhanced1)
elif k == ord('2'):
cv2.imshow('image', enhanced2a)
elif k == ord('w'):
cv2.imshow('image', enhanced2b)
elif k == ord('3'):
cv2.imshow('image', enhanced3)
elif k == 27:
break
cv2.destroyAllWindows()
return 0
def _preprocess(self):
if self.img == None:
raise ValueError("No image loaded")
if 'preprocess' not in self.params:
return
# Scale the image down if its perimeter exceeds the maximum (if set).
perim = sum(self.img.shape[:2])
max_perim = getattr(self.params.preprocess, 'maximum_perimeter', None)
if max_perim and perim > max_perim:
logging.info("Scaling down...")
rf = float(max_perim) / perim
self.img = cv2.resize(self.img, None, fx=rf, fy=rf)
# Perform color enhancement.
color_enhancement = getattr(self.params.preprocess, 'color_enhancement', None)
if color_enhancement:
for method, args in vars(color_enhancement).iteritems():
if method == 'naik_murthy_linear':
logging.info("Color enhancement...")
self.img = ft.naik_murthy_linear(self.img)
else:
raise ValueError("Unknown color enhancement method '%s'" % method)
# Perform segmentation.
segmentation = getattr(self.params.preprocess, 'segmentation', None)
if segmentation:
logging.info("Segmenting...")
iterations = getattr(segmentation, 'iterations', 5)
margin = getattr(segmentation, 'margin', 1)
output_folder = getattr(segmentation, 'output_folder', None)
# Create a binary mask for the largest contour.
self.mask = common.grabcut(self.img, iterations, None, margin)
self.bin_mask = np.where((self.mask==cv2.GC_FGD) + (self.mask==cv2.GC_PR_FGD), 255, 0).astype('uint8')
contour = ft.get_largest_contour(self.bin_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
if contour == None:
raise ValueError("No contour found for binary image")
self.bin_mask = np.zeros(self.img.shape[:2], dtype=np.uint8)
cv2.drawContours(self.bin_mask, [contour], 0, 255, -1)
# Save the masked image to the output folder.
if output_folder and os.path.isdir(output_folder):
img_masked = cv2.bitwise_and(self.img, self.img, mask=self.bin_mask)
fname = os.path.basename(self.path)
out_path = os.path.join(output_folder, fname)
cv2.imwrite(out_path, img_masked)
def __preprocess(self):
"""Perform preprocessing steps as specified in the configurations.
Preprocessing steps may be:
* Resizing
* Color correction
* Segmentation
This method is executed by :meth:`make`.
"""
if self.img is None:
raise RuntimeError("No image is loaded")
if 'preprocess' not in self.config:
return
# Scale the image down if its perimeter (width+height) exceeds the
# maximum. If a ROI is set, use the perimeter of the ROI instead, or
# else we might end up with a very small ROI.
if self.roi:
perim = sum(self.roi[2:4])
else:
perim = sum(self.img.shape[:2])
rf = 1.0
max_perim = getattr(self.config.preprocess, 'maximum_perimeter', None)
if max_perim and perim > max_perim:
logging.info("Scaling down...")
rf = float(max_perim) / perim
self.img = cv2.resize(self.img, None, fx=rf, fy=rf)
# Account for the resizing factor if a ROI is set.
if self.roi:
self.roi = [int(x*rf) for x in self.roi]
self.roi = tuple(self.roi)
# Perform color enhancement.
color_enhancement = getattr(self.config.preprocess,
'color_enhancement', None)
if color_enhancement:
for method, args in vars(color_enhancement).iteritems():
if method == 'naik_murthy_linear':
logging.info("Color enhancement...")
self.img = ft.naik_murthy_linear(self.img)
else:
raise ConfigurationError("Unknown color enhancement "\
"method '%s'" % method)
# Perform segmentation.
try:
segmentation = self.config.preprocess.segmentation.grabcut
except:
segmentation = {}
if segmentation:
logging.info("Segmenting...")
iters = getattr(segmentation, 'iters', 5)
margin = getattr(segmentation, 'margin', 1)
output_folder = getattr(segmentation, 'output_folder', None)
# Get the main contour.
self.mask = self.__grabcut(self.img, iters, self.roi, margin)
self.bin_mask = np.where((self.mask==cv2.GC_FGD) + \
(self.mask==cv2.GC_PR_FGD), 255, 0).astype('uint8')
contour = ft.get_largest_contour(self.bin_mask, cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
if contour is None:
raise ValueError("No contour found for binary image")
# Create a binary mask of the main contour.
self.bin_mask = np.zeros(self.img.shape[:2], dtype=np.uint8)
cv2.drawContours(self.bin_mask, [contour], 0, 255, -1)
# Save the masked image to the output folder.
if output_folder:
img_masked = cv2.bitwise_and(self.img, self.img,
mask=self.bin_mask)
out_path = os.path.join(output_folder, self.path)
out_dir = os.path.dirname(out_path)
if not os.path.isdir(out_dir):
os.makedirs(out_dir)
cv2.imwrite(out_path, img_masked)
def __preprocess(self):
"""Perform preprocessing steps as specified in the configurations.
Preprocessing steps may be:
* Resizing
* Color correction
* Segmentation or cropping
This method is executed by :meth:`make`.
"""
if self.img is None:
raise RuntimeError("No image is loaded")
if 'preprocess' not in self.config:
return
# Scale the image down if its perimeter (width+height) exceeds the
# maximum. If a ROI is set, use the perimeter of the ROI instead, or
# else we might end up with a very small ROI.
if self.roi:
perim = sum(self.roi[2:4])
else:
perim = sum(self.img.shape[:2])
rf = 1.0
max_perim = getattr(self.config.preprocess, 'maximum_perimeter', None)
if max_perim and perim > max_perim:
logging.info("Scaling down...")
rf = float(max_perim) / perim
self.img = cv2.resize(self.img, None, fx=rf, fy=rf)
# Account for the resizing factor if a ROI is set.
if self.roi:
self.roi = [int(x * rf) for x in self.roi]
self.roi = tuple(self.roi)
# Perform color enhancement.
color_enhancement = getattr(self.config.preprocess,
'color_enhancement', None)
if color_enhancement:
for method, args in vars(color_enhancement).iteritems():
if method == 'naik_murthy_linear':
logging.info("Color enhancement...")
self.img = ft.naik_murthy_linear(self.img)
else:
raise ConfigurationError("Unknown color enhancement "\
"method '%s'" % method)
# Perform segmentation.
try:
segmentation = self.config.preprocess.segmentation.grabcut
except:
segmentation = {}
if segmentation:
logging.info("Segmenting...")
iters = getattr(segmentation, 'iters', 5)
margin = getattr(segmentation, 'margin', 1)
output_folder = getattr(segmentation, 'output_folder', None)
# Get the main contour.
self.mask = self.__grabcut(self.img, iters, self.roi, margin)
self.bin_mask = np.where((self.mask==cv2.GC_FGD) + \
(self.mask==cv2.GC_PR_FGD), 255, 0).astype('uint8')
contour = ft.get_largest_contour(self.bin_mask, cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
if contour is None:
raise ValueError("No contour found for binary image")
# Create a binary mask of the main contour.
self.bin_mask = np.zeros(self.img.shape[:2], dtype=np.uint8)
cv2.drawContours(self.bin_mask, [contour], 0, 255, -1)
# Save the masked image to the output folder.
if output_folder:
img_masked = cv2.bitwise_and(self.img,
self.img,
mask=self.bin_mask)
out_path = os.path.join(output_folder, self.path)
out_dir = os.path.dirname(out_path)
if not os.path.isdir(out_dir):
os.makedirs(out_dir)
cv2.imwrite(out_path, img_masked)
else:
# Crop image in stead of segmenting.
try:
crop = self.config.preprocess.crop
except:
crop = {}
if crop:
logging.info("Cropping image...")
roi_pix = getattr(crop, 'roi_pix', None)
roi_frac = getattr(crop, 'roi_frac', None)
if roi_pix:
# roi_pix is like (x, y, w, h) in pixel units.
if len(roi_pix) != 4:
raise ValueError(
"roi_pix must be a list of four integers.")
for x in roi_pix:
if not (isinstance(x, int) and x >= 0):
raise ValueError(
"roi_pix must be a (x, y, w, h) tuple "
"of integers.")
self.roi = roi_pix
elif roi_frac:
# roi_frac is like (x1, x2, y1, y2) in fractions
# of total img size.
if len(roi_frac) != 4:
raise ValueError(
"roi_frac must be a list of four floats.")
for x in roi_frac:
if not 0 <= x <= 1:
raise ValueError(
"roi_frac must be a (x1, x2, y1, y2) tuple, "
"where the values are floats between 0 and 1.")
if not (roi_frac[0] < roi_frac[1]
and roi_frac[2] < roi_frac[3]):
raise ValueError(
"roi_frac must be a (x1, x2, y1, y2) tuple, "
"where x1 < x2 and y1 < y2.")
# Make ROI like (x, y, w, h).
self.roi = (int(self.img.shape[1] * roi_frac[0]),
int(self.img.shape[0] * roi_frac[2]),
int(self.img.shape[1] * roi_frac[1]) -
int(self.img.shape[1] * roi_frac[0]),
int(self.img.shape[0] * roi_frac[3]) -
int(self.img.shape[0] * roi_frac[2]))
else:
logging.warning("No ROI for cropping found. Proceed "
"without cropping.")
self.roi = (0, 0, self.img.shape[1], self.img.shape[0])
# Crop image to given ROI.
self.img = self.img[self.roi[1]:self.roi[1] + self.roi[3],
self.roi[0]:self.roi[0] + self.roi[2]]
def __preprocess(self):
"""Perform preprocessing steps as specified in the configurations.
Preprocessing steps may be:
* Resizing
* Color correction
* Segmentation or cropping
This method is executed by :meth:`make`.
"""
if self.img is None:
raise RuntimeError("No image is loaded")
if 'preprocess' not in self.config:
return
# Scale the image down if its perimeter (width+height) exceeds the
# maximum. If a ROI is set, use the perimeter of the ROI instead, or
# else we might end up with a very small ROI.
if self.roi:
perim = sum(self.roi[2:4])
else:
perim = sum(self.img.shape[:2])
rf = 1.0
max_perim = getattr(self.config.preprocess, 'maximum_perimeter', None)
if max_perim and perim > max_perim:
logging.info("Scaling down...")
rf = float(max_perim) / perim
self.img = cv2.resize(self.img, None, fx=rf, fy=rf)
# Account for the resizing factor if a ROI is set.
if self.roi:
self.roi = [int(x*rf) for x in self.roi]
self.roi = tuple(self.roi)
# Perform color enhancement.
color_enhancement = getattr(self.config.preprocess,
'color_enhancement', None)
if color_enhancement:
for method, args in vars(color_enhancement).iteritems():
if method == 'naik_murthy_linear':
logging.info("Color enhancement...")
self.img = ft.naik_murthy_linear(self.img)
else:
raise ConfigurationError("Unknown color enhancement "\
"method '%s'" % method)
# Perform segmentation.
try:
segmentation = self.config.preprocess.segmentation.grabcut
except:
segmentation = {}
if segmentation:
logging.info("Segmenting...")
iters = getattr(segmentation, 'iters', 5)
margin = getattr(segmentation, 'margin', 1)
output_folder = getattr(segmentation, 'output_folder', None)
# Get the main contour.
self.mask = self.__grabcut(self.img, iters, self.roi, margin)
self.bin_mask = np.where((self.mask==cv2.GC_FGD) + \
(self.mask==cv2.GC_PR_FGD), 255, 0).astype('uint8')
contour = ft.get_largest_contour(self.bin_mask, cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
if contour is None:
raise ValueError("No contour found for binary image")
# Create a binary mask of the main contour.
self.bin_mask = np.zeros(self.img.shape[:2], dtype=np.uint8)
cv2.drawContours(self.bin_mask, [contour], 0, 255, -1)
# Save the masked image to the output folder.
if output_folder:
img_masked = cv2.bitwise_and(self.img, self.img,
mask=self.bin_mask)
out_path = os.path.join(output_folder, self.path)
out_dir = os.path.dirname(out_path)
if not os.path.isdir(out_dir):
os.makedirs(out_dir)
cv2.imwrite(out_path, img_masked)
else:
# Crop image in stead of segmenting.
try:
crop = self.config.preprocess.crop
except:
crop = {}
if crop:
logging.info("Cropping image...")
roi_pix = getattr(crop, 'roi_pix', None)
roi_frac = getattr(crop, 'roi_frac', None)
if roi_pix:
# roi_pix is like (x, y, w, h) in pixel units.
if len(roi_pix) != 4:
raise ValueError(
"roi_pix must be a list of four integers.")
for x in roi_pix:
if not (isinstance(x, int) and x >= 0):
raise ValueError(
"roi_pix must be a (x, y, w, h) tuple "
"of integers.")
self.roi = roi_pix
elif roi_frac:
# roi_frac is like (x1, x2, y1, y2) in fractions
# of total img size.
if len(roi_frac) != 4:
raise ValueError(
"roi_frac must be a list of four floats.")
for x in roi_frac:
if not 0 <= x <= 1:
raise ValueError(
"roi_frac must be a (x1, x2, y1, y2) tuple, "
"where the values are floats between 0 and 1.")
if not (roi_frac[0] < roi_frac[1] and
roi_frac[2] < roi_frac[3]):
raise ValueError(
"roi_frac must be a (x1, x2, y1, y2) tuple, "
"where x1 < x2 and y1 < y2.")
# Make ROI like (x, y, w, h).
self.roi = (int(self.img.shape[1] * roi_frac[0]),
int(self.img.shape[0] * roi_frac[2]),
int(self.img.shape[1] * roi_frac[1]) -
int(self.img.shape[1] * roi_frac[0]),
int(self.img.shape[0] * roi_frac[3]) -
int(self.img.shape[0] * roi_frac[2]))
else:
logging.warning("No ROI for cropping found. Proceed "
"without cropping.")
self.roi = (0, 0, self.img.shape[1], self.img.shape[0])
# Crop image to given ROI.
self.img = self.img[self.roi[1]: self.roi[1] + self.roi[3],
self.roi[0]: self.roi[0] + self.roi[2]]
