def from_binary_image(bin_img, img):
"""Create an ROI from a binary image
Inputs:
bin_img = Binary image to extract an ROI contour from.
img = An RGB or grayscale image to plot the ROI on.
Outputs:
roi_contour = An ROI set of points (contour).
roi_hierarchy = The hierarchy of ROI contour(s).
:param bin_img: numpy.ndarray
:param img: numpy.ndarray
:return roi_contour: list
:return roi_hierarchy: numpy.ndarray
"""
# Autoincrement the device counter
params.device += 1
# Make sure the input bin_img is binary
if len(np.unique(bin_img)) != 2:
fatal_error("Input image is not binary!")
# Use the binary image to create an ROI contour
roi_contour, roi_hierarchy = cv2.findContours(np.copy(bin_img),
cv2.RETR_TREE,
cv2.CHAIN_APPROX_NONE)[-2:]
# Draw the ROI if requested
if params.debug is not None:
_draw_roi(img=img, roi_contour=roi_contour)
return roi_contour, roi_hierarchy
def grab_random(database, random, outdir, imgtype):
# Does the database exist?
if not os.path.exists(database):
pcv.fatal_error("The database file " + str(database) + " does not exist")
# Open a connection
try:
db = sq.connect(database)
except sq.Error as e:
print("Error %s:" % e.args[0])
else:
if imgtype == "VIS":
# Get the headers for metadata and headers for features these will be the headers of features table
metaimages = pd.read_sql_query('SELECT * FROM metadata INNER JOIN analysis_images ON '
'metadata.image_id=analysis_images.image_id where '
'analysis_images.type=="mask" and metadata.imgtype=="VIS"', db)
elif imgtype == "NIR":
# Get the headers for metadata and headers for features these will be the headers of features table
metaimages = pd.read_sql_query('SELECT * FROM metadata INNER JOIN analysis_images ON '
'metadata.image_id=analysis_images.image_id where '
'analysis_images.type=="mask" and metadata.imgtype=="NIR"', db)
elif imgtype == "None":
# Get the headers for metadata and headers for features these will be the headers of features table
metaimages = pd.read_sql_query('SELECT * FROM metadata INNER JOIN analysis_images ON '
'metadata.image_id=analysis_images.image_id where '
'analysis_images.type=="mask" and metadata.imgtype=="none"', db)
else:
pcv.fatal_error("imgtype is not VIS, NIR or None")
sorted = metaimages.sort_values(['timestamp'])
nrowsorted = sorted.shape[0]
chunksfactor = nrowsorted / float(random)
random_index_list = []
for i in range(2, random + 1, 1):
x = int((i - 1) * chunksfactor)
y = int(i * chunksfactor)
randnum = randrange(x, y)
random_index_list.append(randnum)
maskdir = os.path.join(outdir, "training-mask-images")
oridir = os.path.join(outdir, "training-ori-images")
if not os.path.exists(maskdir):
os.makedirs(maskdir)
if not os.path.exists(oridir):
os.makedirs(oridir)
for x in random_index_list:
selectmask = str(sorted.iloc[[x - 1]]['image_path'].item())
selectori = str(sorted.iloc[[x - 1]]['image'].item())
copy(selectmask, maskdir + "/")
copy(selectori, oridir + "/")
def db_lookup(database, ids, outdir, type, vis=False, nir=False, flu=False):
# Does the database exist?
if not os.path.exists(database):
pcv.fatal_error("The database file " + str(database) + " does not exist");
# Open a connection
try:
connect=sq.connect(database)
except sq.Error, e:
print("Error %s:" % e.args[0])
def db_lookup(database, outdir, type):
# Does the database exist?
if not os.path.exists(database):
pcv.fatal_error("The database file " + str(database) + " does not exist");
# Open a connection
try:
connect=sq.connect(database)
except sq.Error, e:
print("Error %s:" % e.args[0])
def grab_random(database,random, outdir, imgtype):
# Does the database exist?
if not os.path.exists(database):
pcv.fatal_error("The database file " + str(database) + " does not exist");
# Open a connection
try:
connect=sq.connect(database)
except sq.Error, e:
print("Error %s:" % e.args[0])
def main():
# Get options
args = options()
# Does the database exist?
if not os.path.exists(args.database):
pcv.fatal_error("The database file " + str(args.database) + " does not exist");
# Open a connection
try:
connect=sq.connect(args.database)
except sq.Error, e:
print("Error %s:" % e.args[0])
def main():
# Get options
args = options()
# Does the database exist?
if not os.path.exists(args.database):
pcv.fatal_error("The database file " + str(args.database) + " does not exist");
# Open a connection
try:
connect=sq.connect(args.database)
except sq.Error, e:
print("Error %s:" % e.args[0])
def db_lookup(database,
outdir,
queries,
vis=False,
nir=False,
psii=False,
verbose=False):
# Does the database exist?
if not os.path.exists(database):
pcv.fatal_error("The database file " + str(database) +
" does not exist")
# Open a connection
try:
connect = sq.connect(database)
except sq.Error as e:
IOError("Error %s:" % e.args[0])
else:
# Replace the row_factory result constructor with a dictionary constructor
connect.row_factory = dict_factory
# Change the text output format from unicode to UTF-8
connect.text_factory = str
# Database handler
db = connect.cursor()
for query in queries:
query = 'select * from metadata where ' + str(query)
if verbose:
print(query)
for row in (db.execute(query)):
dt = datetime.datetime.strptime(
row['timestamp'],
"%Y-%m-%d %H:%M:%S.%f").strftime('%Y-%m-%d-%H-%M-%S')
if vis and row['imgtype'] == 'VIS':
img_name = os.path.join(
outdir, row['plantbarcode'] + "_" + dt + "_" +
os.path.basename(row['image']))
copy(row['image'], img_name)
if nir and row['imgtype'] == 'NIR':
img_name = os.path.join(
outdir, row['plantbarcode'] + "_" + dt + "_" +
os.path.basename(row['image']))
copy(row['image'], img_name)
if psii and row['imgtype'] == 'PSII':
images = row['image'].split(',')
for image in images:
img_name = os.path.join(
outdir, row['plantbarcode'] + "_" + dt + "_" +
os.path.basename(image))
copy(image, img_name)
def grab_random(database, random, imgtype, camera, outdir, verbose):
# Does the database exist?
if not os.path.exists(database):
pcv.fatal_error("The database file " + str(database) +
" does not exist")
# Open a connection
try:
connect = sq.connect(database)
except sq.Error as e:
print("Error %s:" % e.args[0])
else:
# Replace the row_factory result constructor with a dictionary constructor
connect.row_factory = dict_factory
# Change the text output format from unicode to UTF-8
connect.text_factory = str
# Database handler
db = connect.cursor()
imageid_list = []
num = random
if verbose:
print(num)
list_random = db.execute(
'select * from metadata where imgtype=? and camera=? order by random() limit ?',
(
imgtype,
camera,
num,
))
for i, x in enumerate(list_random):
imgid = x['image_id']
imageid_list.append(imgid)
if verbose:
print(imageid_list)
for imgid in imageid_list:
get_image = db.execute('select * from metadata where image_id=?',
(imgid, ))
for row in get_image:
dt = datetime.datetime.strptime(
row['timestamp'],
"%Y-%m-%d %H:%M:%S.%f").strftime('%Y-%m-%d-%H-%M-%S')
img_name = os.path.join(
outdir, row['plantbarcode'] + "_" + dt + "_" +
os.path.basename(row['image']))
copy(row['image'], img_name)
if verbose:
print("copying")
print(img_name)
def ellipse(x, y, r1, r2, angle, img):
"""Create an elliptical ROI.
Inputs:
x = The x-coordinate of the center of the ellipse.
y = The y-coordinate of the center of the ellipse.
r1 = The radius of the major axis.
r2 = The radius of the minor axis.
angle = The angle of rotation of the major axis.
img = An RGB or grayscale image to plot the ROI on in debug mode.
Outputs:
roi_contour = An ROI set of points (contour).
roi_hierarchy = The hierarchy of ROI contour(s).
:param x: int
:param y: int
:param r1: int
:param r2: int
:param angle: int
:param img: numpy.ndarray
:return roi_contour: list
:return roi_hierarchy: numpy.ndarray
"""
# Autoincrement the device counter
params.device += 1
# Get the height and width of the reference image
height, width = np.shape(img)[:2]
# Initialize a binary image of the ellipse
bin_img = np.zeros((height, width), dtype=np.uint8)
# Draw the ellipse on the binary image
cv2.ellipse(bin_img, (x, y), (r1, r2), angle, 0, 360, 255, -1)
if np.sum(bin_img[0, :]) + np.sum(bin_img[-1, :]) + np.sum(
bin_img[:, 0]) + np.sum(bin_img[:, -1]) > 0:
fatal_error("The ROI extends outside of the image!")
# Use the binary image to create an ROI contour
roi_contour, roi_hierarchy = cv2.findContours(np.copy(bin_img),
cv2.RETR_TREE,
cv2.CHAIN_APPROX_NONE)[-2:]
# Draw the ROI if requested
if params.debug is not None:
_draw_roi(img=img, roi_contour=roi_contour)
return roi_contour, roi_hierarchy
def rectangle(x, y, h, w, img):
"""Create a rectangular ROI.
Inputs:
x = The x-coordinate of the upper left corner of the rectangle.
y = The y-coordinate of the upper left corner of the rectangle.
h = The height of the rectangle.
w = The width of the rectangle.
img = An RGB or grayscale image to plot the ROI on in debug mode.
Outputs:
roi_contour = An ROI set of points (contour).
roi_hierarchy = The hierarchy of ROI contour(s).
:param x: int
:param y: int
:param h: int
:param w: int
:param img: numpy.ndarray
:return roi_contour: list
:return roi_hierarchy: numpy.ndarray
"""
# Autoincrement the device counter
params.device += 1
# Get the height and width of the reference image
height, width = np.shape(img)[:2]
# Check whether the ROI is correctly bounded inside the image
if x < 0 or y < 0 or x + w > width or y + h > height:
fatal_error("The ROI extends outside of the image!")
# Create the rectangle contour vertices
pt1 = [x, y]
pt2 = [x, y + h - 1]
pt3 = [x + w - 1, y + h - 1]
pt4 = [x + w - 1, y]
# Create the ROI contour
roi_contour = [np.array([[pt1], [pt2], [pt3], [pt4]], dtype=np.int32)]
roi_hierarchy = np.array([[[-1, -1, -1, -1]]], dtype=np.int32)
# Draw the ROI if requested
if params.debug is not None:
_draw_roi(img=img, roi_contour=roi_contour)
return roi_contour, roi_hierarchy
def circle(x, y, r, img):
"""Create a circular ROI.
Inputs:
x = The x-coordinate of the center of the circle.
y = The y-coordinate of the center of the circle.
r = The radius of the circle.
img = An RGB or grayscale image to plot the ROI on in debug mode.
Outputs:
roi_contour = An ROI set of points (contour).
roi_hierarchy = The hierarchy of ROI contour(s).
:param x: int
:param y: int
:param r: int
:param img: numpy.ndarray
:return roi_contour: list
:return roi_hierarchy: numpy.ndarray
"""
# Autoincrement the device counter
params.device += 1
# Get the height and width of the reference image
height, width = np.shape(img)[:2]
# Check whether the ROI is correctly bounded inside the image
if x - r < 0 or x + r > width or y - r < 0 or y + r > height:
fatal_error("The ROI extends outside of the image!")
# Initialize a binary image of the circle
bin_img = np.zeros((height, width), dtype=np.uint8)
# Draw the circle on the binary image
cv2.circle(bin_img, (x, y), r, 255, -1)
# Use the binary image to create an ROI contour
roi_contour, roi_hierarchy = cv2.findContours(np.copy(bin_img),
cv2.RETR_TREE,
cv2.CHAIN_APPROX_NONE)[-2:]
# Draw the ROI if requested
if params.debug is not None:
_draw_roi(img=img, roi_contour=roi_contour)
return roi_contour, roi_hierarchy
def handle_vis_output(directory, imgtype, outdir, action):
# directory = path to directory you want to grab images from
# imgtype = type of output image you want to move or copy (options are rgb_slice, pseudo_on_img, pseudo_on_white, shapes, or, histogram)
# outdir = where you want the images to go
# action = either 'copy' or 'move'
if imgtype == 'rgb_slice':
path = str(directory)
opendir = os.listdir(path)
for filename in opendir:
if re.search("rgb_norm_slice\.png$", filename):
fromDirectory = str(directory) + str(filename)
toDirectory = str(outdir) + str(filename)
if action == 'copy':
distutils.file_util.copy_file(fromDirectory, toDirectory)
elif action == 'move':
distutils.file_util.move_file(fromDirectory, toDirectory)
else:
pcv.fatal_error('action' +
(str(action) + ' is not move or copy'))
else:
pcv.fatal_error("Sorry no " + str(imgtype) + " images found")
elif imgtype == 'pseudo_on_img':
path = str(directory)
opendir = os.listdir(path)
for filename in opendir:
if re.search("pseudo_on_img\.png$", filename):
fromDirectory = str(directory) + str(filename)
toDirectory = str(outdir) + str(filename)
if action == 'copy':
distutils.file_util.copy_file(fromDirectory, toDirectory)
elif action == 'move':
distutils.file_util.move_file(fromDirectory, toDirectory)
else:
pcv.fatal_error('action' +
(str(action) + ' is not move or copy'))
else:
pcv.fatal_error("Sorry no " + str(imgtype) + " images found")
elif imgtype == 'pseudo_on_white':
path = str(directory)
opendir = os.listdir(path)
for filename in opendir:
if re.search("pseudo_on_white\.png$", filename):
fromDirectory = str(directory) + str(filename)
toDirectory = str(outdir) + str(filename)
if action == 'copy':
distutils.file_util.copy_file(fromDirectory, toDirectory)
elif action == 'move':
distutils.file_util.move_file(fromDirectory, toDirectory)
else:
pcv.fatal_error('action' +
(str(action) + ' is not move or copy'))
else:
pcv.fatal_error("Sorry no " + str(imgtype) + " images found")
elif imgtype == 'shapes':
path = str(directory)
opendir = os.listdir(path)
for filename in opendir:
if re.search("shapes\.png$", filename):
fromDirectory = str(directory) + str(filename)
toDirectory = str(outdir) + str(filename)
if action == 'copy':
distutils.file_util.copy_file(fromDirectory, toDirectory)
elif action == 'move':
distutils.file_util.move_file(fromDirectory, toDirectory)
else:
pcv.fatal_error('action' +
(str(action) + ' is not move or copy'))
else:
pcv.fatal_error("Sorry no " + str(imgtype) + " images found")
elif imgtype == 'histogram':
path = str(directory)
opendir = os.listdir(path)
for filename in opendir:
if re.search("hist\.png$", filename):
fromDirectory = str(directory) + str(filename)
toDirectory = str(outdir) + str(filename)
if action == 'copy':
distutils.file_util.copy_file(fromDirectory, toDirectory)
elif action == 'move':
distutils.file_util.move_file(fromDirectory, toDirectory)
else:
pcv.fatal_error('action' +
(str(action) + ' is not move or copy'))
else:
pcv.fatal_error("Sorry no " + str(imgtype) + " images found")
else:
pcv.fatal_error('imgtype' + (
str(imgtype) +
' is not rgb_slice, pseudo_on_img, pseudo_on_white, shapes, or, histogram!'
))
def define_multi_roi(img,
device,
debug=False,
roi_file=None,
roi_input='default',
rows=None,
col=None,
shape=None,
rad=None,
dist_x=None,
dist_y=None,
adjust_x=False,
adjust_y=False):
#If you have very irregularly spaced ROI (that stays consistent between images), it is likely easiest to provide a file with an ROI
#But remember that the ROIs can capture objects outside of their borders as long as the object is connected (partially inside ROI) so some irregularities are fine
# img= img to overlay roi
# roi_file= default is None, else the user can input an ROI image, object area shoud be white and background area should be black.
# roi_input= type of image that the roi_file is, either 'binary', 'rgb' or 'default' (no ROI inputted)
# debug= True/False, if True, print image
# rows= number of rows of rois
# col= number of columns of rois
# shape= None, 'circle', or 'square'
# rad= radius or height/width of shape
# dist_x= distance between edges on the x axis
# dist_y= distance between edges on the y axis
# adjust_x= distance to move set of roi in the x direction
# adjust_y= distance to move set of roi in the y direction
device += 1
ori_img = np.copy(img)
if len(np.shape(img)) == 3:
ix, iy, iz = np.shape(img)
else:
ix, iy = np.shape(img)
#Allows user to use the default ROI or input their own RGB or binary image (made with imagej or some other program) as a base ROI (that can be adjusted below if necessary)
if roi_input == 'rgb':
hsv = cv2.cvtColor(roi_file, cv2.COLOR_BGR2HSV)
h, s, v = cv2.split(hsv)
ret, v_img = cv2.threshold(v, 0, 255, cv2.THRESH_BINARY)
roi_contour, roi_hierarchy = cv2.findContours(v_img, cv2.RETR_TREE,
cv2.CHAIN_APPROX_NONE)
if debug:
print_image(roi_file, (str(device) + '_roi.png'))
elif roi_input == 'binary':
roi_contour, roi_hierarchy = cv2.findContours(roi_file, cv2.RETR_TREE,
cv2.CHAIN_APPROX_NONE)
if debug:
print_image(roi_file, (str(device) + '_roi.png'))
elif roi_input == 'default':
size = ix, iy
roi_background = np.zeros(size, dtype=np.uint8)
roi_size = (ix - 5), (iy - 5)
roi = np.zeros(roi_size, dtype=np.uint8)
roi1 = roi + 1
roi_contour, roi_heirarchy = cv2.findContours(roi1, cv2.RETR_TREE,
cv2.CHAIN_APPROX_NONE)
cv2.drawContours(roi_background, roi_contour[0], -1, (255, 0, 0), 5)
else:
fatal_error('ROI Input' + str(roi_input) +
' is not "binary", "rgb" or "default roi"!')
print roi_contour
print v
##If the ROI is exactly in the 'correct' position
#if adjust_x==False and adjust_y==False:
# if roi_input=='rgb' or roi_input=='binary':
# size = ix,iy,3
# background = np.zeros(size, dtype=np.uint8)
# roi_contour1=roi_contour+background
# roi_heirarchy1=roi_heirarchy
# cv2.drawContours(ori_img,roi_contour1[0],-1,(255,0,0),5)
# if debug:
# print_image(ori_img,(str(device)+'ori_roi.png'))
# #return device,roi_contour1,roi_heirarchy1
#for cnt in roi_contour:
# size = ix,iy,3
# background = np.zeros(size, dtype=np.uint8)
# if shape=='square':
# x,y,w,h = cv2.boundingRect(cnt)
# cv2.rectangle(background,(x,y),(x+w,y+h),(0,255,0),5)
# rect = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# rect_contour,hierarchy = cv2.findContours(rect,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,rect_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, rect_contour, hierarchy
# elif shape== 'circle':
# x,y,w,h = cv2.boundingRect(cnt)
# center = (int(w/2),int(h/2))
# if h>w:
# radius = int(w/2)
# cv2.circle(background,center,radius,(255,255,255),-1)
# circle = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# circle_contour,hierarchy = cv2.findContours(circle,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,circle_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, circle_contour, hierarchy
# else:
# radius = int(h/2)
# cv2.circle(background,center,radius,(255,255,255),-1)
# circle = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# circle_contour,hierarchy = cv2.findContours(circle,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,circle_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, circle_contour, hierarchy
# elif shape== 'ellipse':
# x,y,w,h = cv2.boundingRect(cnt)
# center = (int(w/2),int(h/2))
# if w>h:
# cv2.ellipse(background,center,(w/2,h/2),0,0,360, (0,255,0), 2)
# ellipse = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# ellipse_contour,hierarchy = cv2.findContours(ellipse,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,ellipse_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, ellipse_contour, hierarchy
# else:
# cv2.ellipse(ori_img,center,(h/2,w/2),0,0,360, (0,255,0), 2)
# cv2.ellipse(background,center,(h/2,w/2),0,0,360, (0,255,0), 2)
# ellipse = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# ellipse_contour,hierarchy = cv2.findContours(ellipse,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,ellipse_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, ellipse_contour, hierarchy
# else:
# fatal_error('Shape' + str(shape) + ' is not "rectangle", "circle", or "ellipse"!')
#Adjust ROI moves the inputted or created ROI
return device
#def define_roi(img, shape, device, roi=None, roi_input='default', debug=False, adjust=False, x_adj=0, y_adj=0, w_adj=0, h_adj=0):
# # img = img to overlay roi
# # roi =default (None) or user input ROI image, object area should be white and background should be black, has not been optimized for more than one ROI
# # roi_input = type of file roi_base is, either 'binary', 'rgb', or 'default' (no ROI inputted)
# # shape = desired shape of final roi, either 'rectangle' or 'circle', if user inputs rectangular roi but chooses 'circle' for shape then a circle is fitted around rectangular roi (and vice versa)
# # device = device number. Used to count steps in the pipeline
# # debug = True/False. If True, print image
# # adjust= either 'True' or 'False', if 'True' allows user to adjust ROI
# # x_adj = adjust center along x axis
# # y_adj = adjust center along y axis
# # w_adj = adjust width
# # h_adj = adjust height
#
# device += 1
# ori_img=np.copy(img)
# if len(np.shape(img))==3:
# ix,iy,iz=np.shape(img)
# else:
# ix,iy=np.shape(img)
#
# #Allows user to use the default ROI or input their own RGB or binary image (made with imagej or some other program) as a base ROI (that can be adjusted below)
# if roi_input== 'rgb':
# hsv = cv2.cvtColor(roi, cv2.COLOR_BGR2HSV)
# h,s,v = cv2.split(hsv)
# ret,v_img = cv2.threshold(v, 0, 255, cv2.THRESH_BINARY)
# roi_contour,hierarchy = cv2.findContours(v_img,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# elif roi_input== 'binary':
# roi_contour,hierarchy = cv2.findContours(rois,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# elif roi_input=='default':
# size = ix,iy
# roi_background = np.zeros(size, dtype=np.uint8)
# roi_size=(ix-5),(iy-5)
# roi=np.zeros(roi_size, dtype=np.uint8)
# roi1=roi+1
# roi_contour,roi_heirarchy=cv2.findContours(roi1,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(roi_background,roi_contour[0],-1, (255,0,0),5)
# if adjust==True:
# if x_adj>0 and w_adj>0:
# fatal_error('Adjusted ROI position is out of frame, this will cause problems in detecting objects')
# elif y_adj>0 and h_adj>0:
# fatal_error('Adjusted ROI position is out of frame, this will cause problems in detecting objects')
# elif x_adj<0 or y_adj<0:
# fatal_error('Adjusted ROI position is out of frame, this will cause problems in detecting objects')
# else:
# fatal_error('ROI Input' + str(roi_input) + ' is not "binary", "rgb" or "default roi"!')
#
# #If the ROI is exactly in the 'correct' position
# if adjust==False:
# for cnt in roi_contour:
# size = ix,iy,3
# background = np.zeros(size, dtype=np.uint8)
# if shape=='rectangle':
# x,y,w,h = cv2.boundingRect(cnt)
# cv2.rectangle(background,(x,y),(x+w,y+h),(0,255,0),5)
# rect = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# rect_contour,hierarchy = cv2.findContours(rect,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,rect_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, rect_contour, hierarchy
# elif shape== 'circle':
# x,y,w,h = cv2.boundingRect(cnt)
# center = (int(w/2),int(h/2))
# if h>w:
# radius = int(w/2)
# cv2.circle(background,center,radius,(255,255,255),-1)
# circle = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# circle_contour,hierarchy = cv2.findContours(circle,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,circle_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, circle_contour, hierarchy
# else:
# radius = int(h/2)
# cv2.circle(background,center,radius,(255,255,255),-1)
# circle = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# circle_contour,hierarchy = cv2.findContours(circle,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,circle_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, circle_contour, hierarchy
# elif shape== 'ellipse':
# x,y,w,h = cv2.boundingRect(cnt)
# center = (int(w/2),int(h/2))
# if w>h:
# cv2.ellipse(background,center,(w/2,h/2),0,0,360, (0,255,0), 2)
# ellipse = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# ellipse_contour,hierarchy = cv2.findContours(ellipse,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,ellipse_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, ellipse_contour, hierarchy
# else:
# cv2.ellipse(ori_img,center,(h/2,w/2),0,0,360, (0,255,0), 2)
# cv2.ellipse(background,center,(h/2,w/2),0,0,360, (0,255,0), 2)
# ellipse = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# ellipse_contour,hierarchy = cv2.findContours(ellipse,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,ellipse_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, ellipse_contour, hierarchy
# else:
# fatal_error('Shape' + str(shape) + ' is not "rectangle", "circle", or "ellipse"!')
#
# #If the user wants to change the size of the ROI or adjust ROI position
# if adjust==True:
# sys.stderr.write('WARNING: Make sure ROI is COMPLETELY in frame or object detection will not perform properly\n')
# if x_adj==0 and y_adj==0 and w_adj==0 and h_adj==0:
# fatal_error( 'If adjust is true then x_adj, y_adj, w_adj or h_adj must have a non-zero value')
# else:
# for cnt in roi_contour:
# size = ix,iy, 3
# background = np.zeros(size, dtype=np.uint8)
# if shape=='rectangle':
# x,y,w,h = cv2.boundingRect(cnt)
# x1=x+x_adj
# y1=y+y_adj
# w1=w+w_adj
# h1=h+h_adj
# cv2.rectangle(background,(x1,y1),(x+w1,y+h1),(0,255,0),1)
# rect = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# rect_contour,hierarchy = cv2.findContours(rect,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,rect_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, rect_contour, hierarchy
# elif shape== 'circle':
# x,y,w,h = cv2.boundingRect(cnt)
# x1=x+x_adj
# y1=y+y_adj
# w1=w+w_adj
# h1=h+h_adj
# center = (int((w+x1)/2),int((h+y1)/2))
# if h>w:
# radius = int(w1/2)
# cv2.circle(background,center,radius,(255,255,255),-1)
# circle = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# circle_contour,hierarchy = cv2.findContours(circle,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,circle_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, circle_contour, hierarchy
# else:
# radius = int(h1/2)
# cv2.circle(background,center,radius,(255,255,255),-1)
# circle = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# circle_contour,hierarchy = cv2.findContours(circle,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,circle_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, circle_contour, hierarchy
# elif shape== 'ellipse':
# x,y,w,h = cv2.boundingRect(cnt)
# x1=x+x_adj
# y1=y+y_adj
# w1=w+w_adj
# h1=h+h_adj
# center = (int((w+x1)/2),int((h+y1)/2))
# if w>h:
# cv2.ellipse(background,center,(w1/2,h1/2),0,0,360, (0,255,0), 2)
# ellipse = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# ellipse_contour,hierarchy = cv2.findContours(ellipse,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,ellipse_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, ellipse_contour, hierarchy
# else:
# cv2.ellipse(background,center,(h1/2,w1/2),0,0,360, (0,255,0), 2)
# ellipse = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# ellipse_contour,hierarchy = cv2.findContours(ellipse,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,ellipse_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, ellipse_contour, hierarchy
# else:
# fatal_error('Shape' + str(shape) + ' is not "rectangle", "circle", or "ellipse"!')
def test_plantcv_fatal_error():
# Verify that the fatal_error function raises a RuntimeError
with pytest.raises(RuntimeError):
pcv.fatal_error("Test error")
def handle_vis_output(directory,imgtype,outdir,action):
# directory = path to directory you want to grab images from
# imgtype = type of output image you want to move or copy (options are rgb_slice, pseudo_on_img, pseudo_on_white, shapes, or, histogram)
# outdir = where you want the images to go
# action = either 'copy' or 'move'
if imgtype=='rgb_slice':
path=str(directory)
opendir=os.listdir(path)
for filename in opendir:
if re.search("rgb_norm_slice\.png$",filename):
fromDirectory = str(directory)+str(filename)
toDirectory = str(outdir)+str(filename)
if action=='copy':
distutils.file_util.copy_file(fromDirectory, toDirectory)
elif action=='move':
distutils.file_util.move_file(fromDirectory, toDirectory)
else:
pcv.fatal_error('action' + (str(action) + ' is not move or copy'))
else:
pcv.fatal_error("Sorry no "+str(imgtype)+ " images found")
elif imgtype=='pseudo_on_img':
path=str(directory)
opendir=os.listdir(path)
for filename in opendir:
if re.search("pseudo_on_img\.png$",filename):
fromDirectory = str(directory)+str(filename)
toDirectory = str(outdir)+str(filename)
if action=='copy':
distutils.file_util.copy_file(fromDirectory, toDirectory)
elif action=='move':
distutils.file_util.move_file(fromDirectory, toDirectory)
else:
pcv.fatal_error('action' + (str(action) + ' is not move or copy'))
else:
pcv.fatal_error("Sorry no "+str(imgtype)+ " images found")
elif imgtype=='pseudo_on_white':
path=str(directory)
opendir=os.listdir(path)
for filename in opendir:
if re.search("pseudo_on_white\.png$",filename):
fromDirectory = str(directory)+str(filename)
toDirectory = str(outdir)+str(filename)
if action=='copy':
distutils.file_util.copy_file(fromDirectory, toDirectory)
elif action=='move':
distutils.file_util.move_file(fromDirectory, toDirectory)
else:
pcv.fatal_error('action' + (str(action) + ' is not move or copy'))
else:
pcv.fatal_error("Sorry no "+str(imgtype)+ " images found")
elif imgtype=='shapes':
path=str(directory)
opendir=os.listdir(path)
for filename in opendir:
if re.search("shapes\.png$",filename):
fromDirectory = str(directory)+str(filename)
toDirectory = str(outdir)+str(filename)
if action=='copy':
distutils.file_util.copy_file(fromDirectory, toDirectory)
elif action=='move':
distutils.file_util.move_file(fromDirectory, toDirectory)
else:
pcv.fatal_error('action' + (str(action) + ' is not move or copy'))
else:
pcv.fatal_error("Sorry no "+str(imgtype)+ " images found")
elif imgtype=='histogram':
path=str(directory)
opendir=os.listdir(path)
for filename in opendir:
if re.search("hist\.png$",filename):
fromDirectory = str(directory)+str(filename)
toDirectory = str(outdir)+str(filename)
if action=='copy':
distutils.file_util.copy_file(fromDirectory, toDirectory)
elif action=='move':
distutils.file_util.move_file(fromDirectory, toDirectory)
else:
pcv.fatal_error('action' + (str(action) + ' is not move or copy'))
else:
pcv.fatal_error("Sorry no "+str(imgtype)+ " images found")
else:
pcv.fatal_error('imgtype' + (str(imgtype) + ' is not rgb_slice, pseudo_on_img, pseudo_on_white, shapes, or, histogram!'))
# Get the headers for metadata and headers for features these will be the headers of features table
metaimages = pd.read_sql_query('SELECT * FROM metadata INNER JOIN analysis_images ON '
'metadata.image_id=analysis_images.image_id where analysis_images.type=="mask" '
'and metadata.imgtype=="VIS"', db)
elif imgtype=="NIR":
# Get the headers for metadata and headers for features these will be the headers of features table
metaimages = pd.read_sql_query('SELECT * FROM metadata INNER JOIN analysis_images ON '
'metadata.image_id=analysis_images.image_id where analysis_images.type=="mask" '
'and metadata.imgtype=="NIR"', db)
elif imgtype=="None":
# Get the headers for metadata and headers for features these will be the headers of features table
metaimages = pd.read_sql_query('SELECT * FROM metadata INNER JOIN analysis_images ON '
'metadata.image_id=analysis_images.image_id where analysis_images.type=="mask" '
'and metadata.imgtype=="none"', db)
else:
pcv.fatal_error("imgtype is not VIS, NIR or None")
sorted=metaimages.sort_values(['timestamp'])
nrowsorted=sorted.shape[0]
chunksfactor=nrowsorted/float(random)
random_index_list=[]
for i in range(2,random+1,1):
x=int((i-1)*chunksfactor)
y=int((i)*chunksfactor)
randnum=randrange(x,y)
random_index_list.append(randnum)
def test_plantcv_fatal_error():
# Verify that the fatal_error function raises a RuntimeError
with pytest.raises(RuntimeError):
pcv.fatal_error("Test error")
def define_multi_roi(img, device, debug=False, roi_file=None, roi_input='default', rows=None, col=None, shape=None, rad=None, dist_x=None, dist_y=None, adjust_x=False, adjust_y=False):
#If you have very irregularly spaced ROI (that stays consistent between images), it is likely easiest to provide a file with an ROI
#But remember that the ROIs can capture objects outside of their borders as long as the object is connected (partially inside ROI) so some irregularities are fine
# img= img to overlay roi
# roi_file= default is None, else the user can input an ROI image, object area shoud be white and background area should be black.
# roi_input= type of image that the roi_file is, either 'binary', 'rgb' or 'default' (no ROI inputted)
# debug= True/False, if True, print image
# rows= number of rows of rois
# col= number of columns of rois
# shape= None, 'circle', or 'square'
# rad= radius or height/width of shape
# dist_x= distance between edges on the x axis
# dist_y= distance between edges on the y axis
# adjust_x= distance to move set of roi in the x direction
# adjust_y= distance to move set of roi in the y direction
device +=1
ori_img=np.copy(img)
if len(np.shape(img))==3:
ix,iy,iz=np.shape(img)
else:
ix,iy=np.shape(img)
#Allows user to use the default ROI or input their own RGB or binary image (made with imagej or some other program) as a base ROI (that can be adjusted below if necessary)
if roi_input== 'rgb':
hsv = cv2.cvtColor(roi_file, cv2.COLOR_BGR2HSV)
h,s,v = cv2.split(hsv)
ret,v_img = cv2.threshold(v, 0, 255, cv2.THRESH_BINARY)
roi_contour,roi_hierarchy = cv2.findContours(v_img,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
if debug:
print_image(roi_file, (str(device) + '_roi.png'))
elif roi_input== 'binary':
roi_contour,roi_hierarchy = cv2.findContours(roi_file,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
if debug:
print_image(roi_file, (str(device) + '_roi.png'))
elif roi_input=='default':
size = ix,iy
roi_background = np.zeros(size, dtype=np.uint8)
roi_size=(ix-5),(iy-5)
roi=np.zeros(roi_size, dtype=np.uint8)
roi1=roi+1
roi_contour,roi_heirarchy=cv2.findContours(roi1,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
cv2.drawContours(roi_background,roi_contour[0],-1, (255,0,0),5)
else:
fatal_error('ROI Input' + str(roi_input) + ' is not "binary", "rgb" or "default roi"!')
print roi_contour
print v
##If the ROI is exactly in the 'correct' position
#if adjust_x==False and adjust_y==False:
# if roi_input=='rgb' or roi_input=='binary':
# size = ix,iy,3
# background = np.zeros(size, dtype=np.uint8)
# roi_contour1=roi_contour+background
# roi_heirarchy1=roi_heirarchy
# cv2.drawContours(ori_img,roi_contour1[0],-1,(255,0,0),5)
# if debug:
# print_image(ori_img,(str(device)+'ori_roi.png'))
# #return device,roi_contour1,roi_heirarchy1
#for cnt in roi_contour:
# size = ix,iy,3
# background = np.zeros(size, dtype=np.uint8)
# if shape=='square':
# x,y,w,h = cv2.boundingRect(cnt)
# cv2.rectangle(background,(x,y),(x+w,y+h),(0,255,0),5)
# rect = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# rect_contour,hierarchy = cv2.findContours(rect,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,rect_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, rect_contour, hierarchy
# elif shape== 'circle':
# x,y,w,h = cv2.boundingRect(cnt)
# center = (int(w/2),int(h/2))
# if h>w:
# radius = int(w/2)
# cv2.circle(background,center,radius,(255,255,255),-1)
# circle = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# circle_contour,hierarchy = cv2.findContours(circle,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,circle_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, circle_contour, hierarchy
# else:
# radius = int(h/2)
# cv2.circle(background,center,radius,(255,255,255),-1)
# circle = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# circle_contour,hierarchy = cv2.findContours(circle,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,circle_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, circle_contour, hierarchy
# elif shape== 'ellipse':
# x,y,w,h = cv2.boundingRect(cnt)
# center = (int(w/2),int(h/2))
# if w>h:
# cv2.ellipse(background,center,(w/2,h/2),0,0,360, (0,255,0), 2)
# ellipse = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# ellipse_contour,hierarchy = cv2.findContours(ellipse,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,ellipse_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, ellipse_contour, hierarchy
# else:
# cv2.ellipse(ori_img,center,(h/2,w/2),0,0,360, (0,255,0), 2)
# cv2.ellipse(background,center,(h/2,w/2),0,0,360, (0,255,0), 2)
# ellipse = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# ellipse_contour,hierarchy = cv2.findContours(ellipse,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,ellipse_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, ellipse_contour, hierarchy
# else:
# fatal_error('Shape' + str(shape) + ' is not "rectangle", "circle", or "ellipse"!')
#Adjust ROI moves the inputted or created ROI
return device
#def define_roi(img, shape, device, roi=None, roi_input='default', debug=False, adjust=False, x_adj=0, y_adj=0, w_adj=0, h_adj=0):
# # img = img to overlay roi
# # roi =default (None) or user input ROI image, object area should be white and background should be black, has not been optimized for more than one ROI
# # roi_input = type of file roi_base is, either 'binary', 'rgb', or 'default' (no ROI inputted)
# # shape = desired shape of final roi, either 'rectangle' or 'circle', if user inputs rectangular roi but chooses 'circle' for shape then a circle is fitted around rectangular roi (and vice versa)
# # device = device number. Used to count steps in the pipeline
# # debug = True/False. If True, print image
# # adjust= either 'True' or 'False', if 'True' allows user to adjust ROI
# # x_adj = adjust center along x axis
# # y_adj = adjust center along y axis
# # w_adj = adjust width
# # h_adj = adjust height
#
# device += 1
# ori_img=np.copy(img)
# if len(np.shape(img))==3:
# ix,iy,iz=np.shape(img)
# else:
# ix,iy=np.shape(img)
#
# #Allows user to use the default ROI or input their own RGB or binary image (made with imagej or some other program) as a base ROI (that can be adjusted below)
# if roi_input== 'rgb':
# hsv = cv2.cvtColor(roi, cv2.COLOR_BGR2HSV)
# h,s,v = cv2.split(hsv)
# ret,v_img = cv2.threshold(v, 0, 255, cv2.THRESH_BINARY)
# roi_contour,hierarchy = cv2.findContours(v_img,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# elif roi_input== 'binary':
# roi_contour,hierarchy = cv2.findContours(rois,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# elif roi_input=='default':
# size = ix,iy
# roi_background = np.zeros(size, dtype=np.uint8)
# roi_size=(ix-5),(iy-5)
# roi=np.zeros(roi_size, dtype=np.uint8)
# roi1=roi+1
# roi_contour,roi_heirarchy=cv2.findContours(roi1,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(roi_background,roi_contour[0],-1, (255,0,0),5)
# if adjust==True:
# if x_adj>0 and w_adj>0:
# fatal_error('Adjusted ROI position is out of frame, this will cause problems in detecting objects')
# elif y_adj>0 and h_adj>0:
# fatal_error('Adjusted ROI position is out of frame, this will cause problems in detecting objects')
# elif x_adj<0 or y_adj<0:
# fatal_error('Adjusted ROI position is out of frame, this will cause problems in detecting objects')
# else:
# fatal_error('ROI Input' + str(roi_input) + ' is not "binary", "rgb" or "default roi"!')
#
# #If the ROI is exactly in the 'correct' position
# if adjust==False:
# for cnt in roi_contour:
# size = ix,iy,3
# background = np.zeros(size, dtype=np.uint8)
# if shape=='rectangle':
# x,y,w,h = cv2.boundingRect(cnt)
# cv2.rectangle(background,(x,y),(x+w,y+h),(0,255,0),5)
# rect = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# rect_contour,hierarchy = cv2.findContours(rect,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,rect_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, rect_contour, hierarchy
# elif shape== 'circle':
# x,y,w,h = cv2.boundingRect(cnt)
# center = (int(w/2),int(h/2))
# if h>w:
# radius = int(w/2)
# cv2.circle(background,center,radius,(255,255,255),-1)
# circle = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# circle_contour,hierarchy = cv2.findContours(circle,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,circle_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, circle_contour, hierarchy
# else:
# radius = int(h/2)
# cv2.circle(background,center,radius,(255,255,255),-1)
# circle = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# circle_contour,hierarchy = cv2.findContours(circle,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,circle_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, circle_contour, hierarchy
# elif shape== 'ellipse':
# x,y,w,h = cv2.boundingRect(cnt)
# center = (int(w/2),int(h/2))
# if w>h:
# cv2.ellipse(background,center,(w/2,h/2),0,0,360, (0,255,0), 2)
# ellipse = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# ellipse_contour,hierarchy = cv2.findContours(ellipse,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,ellipse_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, ellipse_contour, hierarchy
# else:
# cv2.ellipse(ori_img,center,(h/2,w/2),0,0,360, (0,255,0), 2)
# cv2.ellipse(background,center,(h/2,w/2),0,0,360, (0,255,0), 2)
# ellipse = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# ellipse_contour,hierarchy = cv2.findContours(ellipse,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,ellipse_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, ellipse_contour, hierarchy
# else:
# fatal_error('Shape' + str(shape) + ' is not "rectangle", "circle", or "ellipse"!')
#
# #If the user wants to change the size of the ROI or adjust ROI position
# if adjust==True:
# sys.stderr.write('WARNING: Make sure ROI is COMPLETELY in frame or object detection will not perform properly\n')
# if x_adj==0 and y_adj==0 and w_adj==0 and h_adj==0:
# fatal_error( 'If adjust is true then x_adj, y_adj, w_adj or h_adj must have a non-zero value')
# else:
# for cnt in roi_contour:
# size = ix,iy, 3
# background = np.zeros(size, dtype=np.uint8)
# if shape=='rectangle':
# x,y,w,h = cv2.boundingRect(cnt)
# x1=x+x_adj
# y1=y+y_adj
# w1=w+w_adj
# h1=h+h_adj
# cv2.rectangle(background,(x1,y1),(x+w1,y+h1),(0,255,0),1)
# rect = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# rect_contour,hierarchy = cv2.findContours(rect,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,rect_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, rect_contour, hierarchy
# elif shape== 'circle':
# x,y,w,h = cv2.boundingRect(cnt)
# x1=x+x_adj
# y1=y+y_adj
# w1=w+w_adj
# h1=h+h_adj
# center = (int((w+x1)/2),int((h+y1)/2))
# if h>w:
# radius = int(w1/2)
# cv2.circle(background,center,radius,(255,255,255),-1)
# circle = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# circle_contour,hierarchy = cv2.findContours(circle,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,circle_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, circle_contour, hierarchy
# else:
# radius = int(h1/2)
# cv2.circle(background,center,radius,(255,255,255),-1)
# circle = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# circle_contour,hierarchy = cv2.findContours(circle,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,circle_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, circle_contour, hierarchy
# elif shape== 'ellipse':
# x,y,w,h = cv2.boundingRect(cnt)
# x1=x+x_adj
# y1=y+y_adj
# w1=w+w_adj
# h1=h+h_adj
# center = (int((w+x1)/2),int((h+y1)/2))
# if w>h:
# cv2.ellipse(background,center,(w1/2,h1/2),0,0,360, (0,255,0), 2)
# ellipse = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# ellipse_contour,hierarchy = cv2.findContours(ellipse,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,ellipse_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, ellipse_contour, hierarchy
# else:
# cv2.ellipse(background,center,(h1/2,w1/2),0,0,360, (0,255,0), 2)
# ellipse = cv2.cvtColor( background, cv2.COLOR_RGB2GRAY )
# ellipse_contour,hierarchy = cv2.findContours(ellipse,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
# cv2.drawContours(ori_img,ellipse_contour[0],-1, (255,0,0),5)
# if debug:
# print_image(ori_img, (str(device) + '_roi.png'))
# return device, ellipse_contour, hierarchy
# else:
# fatal_error('Shape' + str(shape) + ' is not "rectangle", "circle", or "ellipse"!')
