def loadDistMatrixFromFile(self,filename): #print mnemosyne_dir+filename try: #self.VectDist = cv.CreateMat(5,1,cv.CV_32FC1) #tmpVectDist = cv.Load(mnemosyne_dir+filename, cv.CreateMemStorage(), name="distortion_coefficients") self.VectDist = cv.Load(mnemosyne_dir+filename, cv.CreateMemStorage(), name="distortion_coefficients") #cv.Convert(tmpVectDist, self.VectDist) except: print "Could not load file:",mnemosyne_dir+filename
def loadCamMatrixFromFile(self,filename): #print mnemosyne_dir+filename try: #self.MatCam = cv.CreateMat(3,3,cv.CV_32FC1) #tmpMatCam = cv.Load(mnemosyne_dir+filename, cv.CreateMemStorage(), name="camera_matrix") self.MatCam = cv.Load(mnemosyne_dir+filename, cv.CreateMemStorage(), name="camera_matrix") #cv.Convert(tmpMatCam, self.MatCam) except: print "Could not load file:",mnemosyne_dir+filename
def faces_from_pil_image(pil_image):
"Return a list of (x,y,h,w) tuples for faces detected in the PIL image"
storage = cv.CreateMemStorage(0)
facial_features = cv.Load('haarcascade_frontalface_alt.xml', storage=storage)
cv_im = cv.CreateImageHeader(pil_image.size, cv.IPL_DEPTH_8U, 3)
cv.SetData(cv_im, pil_image.tostring())
faces = cv.HaarDetectObjects(cv_im, facial_features, storage)
# faces includes a `neighbors` field that we aren't going to use here
return [f[0] for f in faces]
def red_eye(self):
self.load_cascade_file()
faces = [
face for face in self.context.request.focal_points
if face.origin == 'Face Detection'
]
if faces:
engine = self.context.modules.engine
mode, data = engine.image_data_as_rgb()
mode = mode.lower()
sz = engine.size
image = cv.CreateImageHeader(sz, cv.IPL_DEPTH_8U, 3)
cv.SetData(image, data)
for face in faces:
face_x = int(face.x - face.width / 2)
face_y = int(face.y - face.height / 2)
face_roi = (int(face_x), int(face_y), int(face.width),
int(face.height))
cv.SetImageROI(image, face_roi)
eyes = cv.HaarDetectObjects(image, self.cascade,
cv.CreateMemStorage(0), HAAR_SCALE,
MIN_NEIGHBORS, HAAR_FLAGS,
MIN_SIZE)
for (x, y, w, h), other in self.filter_eyes(eyes):
# Set the image Region of interest to be the eye area [this reduces processing time]
cv.SetImageROI(image, (face_x + x, face_y + y, w, h))
if self.context.request.debug:
cv.Rectangle(image, (0, 0), (w, h),
cv.RGB(255, 255, 255), 2, 8, 0)
for pixel in self.get_pixels(image, w, h, mode):
green_blue_avg = (pixel['g'] + pixel['b']) / 2
if not green_blue_avg:
red_intensity = RED_THRESHOLD
else:
# Calculate the intensity compared to blue and green average
red_intensity = pixel['r'] / green_blue_avg
# If the red intensity is greater than 2.0, lower the value
if red_intensity >= RED_THRESHOLD:
new_red_value = (pixel['g'] + pixel['b']) / 2
# Insert the new red value for the pixel to the image
cv.Set2D(
image, pixel['y'], pixel['x'],
cv.RGB(new_red_value, pixel['g'], pixel['b']))
# Reset the image region of interest back to full image
cv.ResetImageROI(image)
self.context.modules.engine.set_image_data(image.tostring())
def __init__(self):
self.active = False
#self.depth8 = cv.CreateImage((640,480), 8, 1)
self.depth8 = ProcessContours.DEPTH8
self.sweep_images = [
cv.CreateImage((640, 480), 8, 1) for i in range(64)
]
self.storage = cv.CreateMemStorage(0)
def get_candidates(self, m_d):
'''
Get candidates for this corner from new image
@param m_d: marker_detector
'''
# if this corner is wider then MAX_CORNER_ANGLE, we probably won't
# find it anyway. Instead lets find narrow corners and calculate its
# position
if self.angle > MAX_CORNER_ANGLE: return []
cr = self.get_rectangle(m_d)
cr = correct_rectangle(cr, m_d.size)
if cr is None: return []
m_d.set_ROI(cr)
tmp_img = m_d.tmp_img
gray_img = m_d.gray_img
bw_img = m_d.bw_img
canny = m_d.canny_img
cv.Copy(gray_img, tmp_img)
cv.Threshold(gray_img, bw_img, 125, 255, cv.CV_THRESH_OTSU)
if self.black_inside > 0:
cv.Not(bw_img, bw_img)
cv.Canny(gray_img, canny, 300, 500)
cv.Or(bw_img, canny, bw_img)
tmpim = m_d.canny_img
cv.Copy(bw_img, tmpim)
cv.Set2D(tmpim, 1, 1, 255)
conts = cv.FindContours(tmpim, cv.CreateMemStorage(),
cv.CV_RETR_EXTERNAL)
cv.Zero(tmpim)
m_d.set_ROI()
cv.SetImageROI(tmpim, cr)
result = []
while conts:
aconts = cv.ApproxPoly(conts, cv.CreateMemStorage(),
cv.CV_POLY_APPROX_DP, 2)
nconts = list(aconts)
cv.PolyLine(tmpim, [nconts], True, (255, 255, 255))
self._append_candidates_from_conts(cr, result, nconts, m_d)
conts = conts.h_next()
# print result
# db.show([tmpim,m_d.draw_img], 'tmpim', 0, 0, 0)
return result
def calibrate(cam):
print "\n\nCamera calibration " + str(cam)
intrinsicPath = "/var/www/MuseumVisitors/calibration/calibIntrCam" + str(
cam) + "-R1280x800.yml"
extrinsicPath = "/var/www/MuseumVisitors/calibration/calibExtr_" + str(
cam) + ".yaml"
print "Rotation matrix:"
VectRot = cv2.cv.Load(extrinsicPath,
cv.CreateMemStorage(),
name="Rotation")
MatRot = cv.CreateMat(3, 3, cv.CV_64FC1)
cv.Rodrigues2(VectRot, MatRot)
MatRot = np.matrix(MatRot)
print MatRot
print "Translation vector:"
VectTrans = cv2.cv.Load(extrinsicPath,
cv.CreateMemStorage(),
name="Translation")
VectTrans = np.matrix(VectTrans)
print VectTrans
print "Camera matrix:"
MatCam = cv2.cv.Load(intrinsicPath,
cv.CreateMemStorage(),
name="camera_matrix")
MatCam = np.matrix(MatCam)
print MatCam
RotTrans = np.concatenate((MatRot[0:3, 0:2], VectTrans), axis=1)
print(RotTrans)
Hw = MatCam * RotTrans
print(Hw)
HT = (Hw.T).I
HI2W = Hw.I
HW2I = (HI2W.I).T
print "HI2W:"
print(HI2W)
print "HW2I:"
print(HW2I)
def init_images():
""" Creates all the images we'll need. Is separate from init_globals
since we need to know what size the images are before we can make
them
"""
# get D so that we can change values in it
global D
# Find the size of the image
# We set D.image right before calling this function
D.size = cv.GetSize(D.image)
# Create images for each color channel
D.red = cv.CreateImage(D.size, 8, 1)
D.blue = cv.CreateImage(D.size, 8, 1)
D.green = cv.CreateImage(D.size, 8, 1)
D.hue = cv.CreateImage(D.size, 8, 1)
D.sat = cv.CreateImage(D.size, 8, 1)
D.val = cv.CreateImage(D.size, 8, 1)
# Create images to save the thresholded images to
D.red_threshed = cv.CreateImage(D.size, 8, 1)
D.green_threshed = cv.CreateImage(D.size, 8, 1)
D.blue_threshed = cv.CreateImage(D.size, 8, 1)
D.hue_threshed = cv.CreateImage(D.size, 8, 1)
D.sat_threshed = cv.CreateImage(D.size, 8, 1)
D.val_threshed = cv.CreateImage(D.size, 8, 1)
# The final thresholded result
D.threshed_image = cv.CreateImage(D.size, 8, 1)
# Create an hsv image and a copy for contour-finding
D.hsv = cv.CreateImage(D.size, 8, 3)
D.copy = cv.CreateImage(D.size, 8, 1)
D.storage = cv.CreateMemStorage(0) # Create memory storage for contours
# bunch of keypress values
# So we know what to show, depending on which key is pressed
D.key_dictionary = {
ord('w'): D.threshed_image,
ord('u'): D.red,
ord('i'): D.green,
ord('o'): D.blue,
ord('j'): D.red_threshed,
ord('k'): D.green_threshed,
ord('l'): D.blue_threshed,
ord('a'): D.hue,
ord('s'): D.sat,
ord('d'): D.val,
ord('z'): D.hue_threshed,
ord('x'): D.sat_threshed,
ord('c'): D.val_threshed,
}
# set the default image for the second window
D.current_threshold = D.threshed_image
def detect_and_draw(img, cascade):
# allocate temporary images
gray = cv.CreateImage((img.width, img.height), 8, 1)
small_img = cv.CreateImage((cv.Round(
img.width / image_scale), cv.Round(img.height / image_scale)), 8, 1)
# convert color input image to grayscale
cv.CvtColor(img, gray, cv.CV_BGR2GRAY)
# scale input image for faster processing
cv.Resize(gray, small_img, cv.CV_INTER_LINEAR)
cv.EqualizeHist(small_img, small_img)
window = cv.CreateImage((cv.Round(img.width), cv.Round(img.height)), 8, 3)
if (cascade):
t = cv.GetTickCount()
faces = local_haar_detect(small_img, cascade, cv.CreateMemStorage(0),
haar_scale, min_neighbors, haar_flags,
min_size)
t = cv.GetTickCount() - t
print "detection time = %gms" % (t / (cv.GetTickFrequency() * 1000.))
channels = None
if faces:
for ((x, y, w, h), n) in faces:
# the input to cv.HaarDetectObjects was resized, so scale the
# bounding box of each face and convert it to two CvPoints
pt1 = (cv.Round(
(x + w * .2) * image_scale), cv.Round(y * image_scale))
pt2 = (cv.Round(
(x + w * .8) * image_scale), cv.Round(
(y + h) * image_scale))
window = cv.CreateImage((cv.Round(w * .6) * image_scale,
cv.Round(h) * image_scale), 8, 3)
cv.Smooth(window, window, cv.CV_GAUSSIAN)
channels = [
cv.CreateImage((cv.Round(w * .6) * image_scale,
cv.Round(h) * image_scale), 8, 1),
cv.CreateImage((cv.Round(w * .6) * image_scale,
cv.Round(h) * image_scale), 8, 1),
cv.CreateImage((cv.Round(w * .6) * image_scale,
cv.Round(h) * image_scale), 8, 1)
]
cv.GetRectSubPix(img, window, (cv.Round(
(pt1[0] + pt2[0]) / 2.0), cv.Round(
(pt1[1] + pt2[1]) / 2.0)))
cv.Rectangle(img, pt1, pt2, cv.RGB(255, 0, 0), 3, 8, 0)
cv.Split(window, channels[0], channels[1], channels[2], None)
result.append([
cv.Avg(channels[0])[0],
cv.Avg(channels[1])[0],
cv.Avg(channels[2])[0]
])
cv.ShowImage("result", img)
def _get_approx(self, conts):
'''
Returns contur aproximation
@param conts: conturs
'''
per = cv.ArcLength(conts)
conts = cv.ApproxPoly(conts, cv.CreateMemStorage(),
cv.CV_POLY_APPROX_DP, per * 0.05)
#cv.DrawContours(self.img, conts, (0,0,255), (0,255,0), 4)
return list(conts)
def _get_face_rectangles(self):
cvim = self._pil_to_opencv()
return cv.HaarDetectObjects(
cvim,
self._get_face_classifier(),
cv.CreateMemStorage(0),
1.3, # Scale factor
4, # Minimum neighbors
0, # HAAR Flags
(20, 20))
def __init__(
self, BW
): #Constructor. BW is a binary image in the form of a numpy array
self.BW = BW
cs = cv.FindContours(cv.fromarray(self.BW.astype(np.uint8)),
cv.CreateMemStorage(),
mode=cv.CV_RETR_EXTERNAL) #Finds the contours
counter = 0
centroid = list()
cHull = list()
contours = list()
cHullArea = list()
contourArea = list()
while cs: #Iterate through the CvSeq, cs.
if abs(cv.ContourArea(cs)) > 2000:
contourArea.append(cv.ContourArea(cs))
m = cv.Moments(cs)
try:
m10 = int(cv.GetSpatialMoment(m, 1,
0)) #Spatial moment m10
m00 = int(cv.GetSpatialMoment(m, 0,
0)) #Spatial moment m00
m01 = int(cv.GetSpatialMoment(m, 0,
1)) #Spatial moment m01
centroid.append((int(m10 / m00), int(m01 / m00)))
convexHull = cv.ConvexHull2(cs,
cv.CreateMemStorage(),
return_points=True)
cHullArea.append(cv.ContourArea(convexHull))
cHull.append(list(convexHull))
contours.append(list(cs))
counter += 1
except:
pass
cs = cs.h_next()
self.centroid = centroid
self.counter = counter
self.cHull = cHull
self.contours = contours
self.cHullArea = cHullArea
self.contourArea = contourArea
def extracteur_de_sourires(nom, src): img = cv.GetSubRect(src, (src.width*1/7, src.height*2/3, src.width*5/7, src.height/3)) cpt = 0 for s in all_s : res = cv.HaarDetectObjects(img, s, cv.CreateMemStorage()) if len(res) == 1 : cpt = cpt + 1 if cpt == len(all_s) : print "\tsourire vu dans "+nom cv.SaveImage(result+str(cpt)+"s_"+nom, img)
def find_convex_hull(cvseq):
""" @param cvseq cvseq: an input cvseq from cv.FindContours
@return cvseq hull: convex hull from ConvexHull2
"""
storage = cv.CreateMemStorage(0)
try:
hull = cv.ConvexHull2(cvseq, storage, cv.CV_CLOCKWISE, 1)
except TypeError, e:
print "Find convex hull failed"
return None
def show_faces():
image = video_to_bgr(freenect.sync_get_video()[0])
min_size = (20, 20)
image_scale = 2
haar_scale = 1.2
min_neighbors = 2
haar_flags = 0
gray = cv.CreateImage((image.width, image.height), 8, 1)
small_image = cv.CreateImage((cv.Round(
image.width / image_scale), cv.Round(image.height / image_scale)), 8,
1)
cv.CvtColor(image, gray, cv.CV_BGR2GRAY)
cv.Resize(gray, small_image, cv.CV_INTER_LINEAR)
cv.EqualizeHist(small_image, small_image)
faces = cv.HaarDetectObjects(small_image, face_cascade,
cv.CreateMemStorage(0), haar_scale,
min_neighbors, haar_flags, min_size)
if faces:
for ((x, y, w, h), n) in faces:
pt1 = (int(x * image_scale), int(y * image_scale))
pt2 = (int((x + w) * image_scale), int((y + h) * image_scale))
cv.Rectangle(image, pt1, pt2, cv.RGB(255, 0, 0), 3, 8, 0)
cv.SetImageROI(
image,
(pt1[0], pt1[1], pt2[0] - pt1[0], int(
(pt2[1] - pt1[1]) * 0.7)))
eyes = cv.HaarDetectObjects(image, eye_cascade, cv.CreateMemStorage(0),
haar_scale, min_neighbors, haar_flags,
(15, 15))
if eyes:
for eye in eyes:
cv.Rectangle(image, (eye[0][0], eye[0][1]),
(eye[0][0] + eye[0][2], eye[0][1] + eye[0][3]),
cv.RGB(255, 0, 0), 1, 8, 0)
cv.ResetImageROI(image)
return image
def search_face(self, face_params):
"""
Search on the picture for a face.
Populates faces list.
This function is the only one containing scaling information
Set several Guy information, such as the face size, or the virtual center of the image
:param face_params: The type of file to be used to train the classifier.
:type face_params: string
Once Faces have been found, they are listed and ordered
"""
# Load the input image
in_image = self.load_image()
# Allocate the temporary images
gray = cv.CreateImage((self.in_x, self.in_y),
cv.IPL_DEPTH_8U,
1)
smallImage = cv.CreateImage((cv.Round(self.in_x / face_params.image_scale),
cv.Round (self.in_y / face_params.image_scale)),
cv.IPL_DEPTH_8U ,
1)
# Converts color input image to grayscale
cv.CvtColor(in_image, gray, cv.CV_BGR2GRAY)
# Scales input image for faster processing
cv.Resize(gray, smallImage, cv.CV_INTER_LINEAR)
# Equalizes the histogram
cv.EqualizeHist(smallImage, smallImage)
# Detect the faces
small_faces = cv.HaarDetectObjects(smallImage,
face_params.face_cascade,
cv.CreateMemStorage(0),
face_params.haar_scale,
face_params.min_neighbors,
face_params.haar_flags,
face_params.min_size)
# Resizing faces to full_scale
for face in small_faces:
if len(face): # if faces have been found
((x, y, w, h), n) = face
big_face = ((int(x * face_params.image_scale),
int(y * face_params.image_scale),
int(w * face_params.image_scale),
int(h * face_params.image_scale)), n)
self.faces.append(big_face)
# sorting faces to keep only the most probable one
self.sort_faces()
self.update_center() # finds center of face in image
def track(img, threshold=100):
'''Accepts BGR image and optional object threshold between 0 and 255 (default = 100).
Returns: (x,y) coordinates of centroid if found
(-1,-1) if no centroid was found
None if user hit ESC
'''
cascade = cv.Load("haarcascade_frontalface_alt_tree.xml")
#cascade = cv.Load("haarcascade_frontalface_default.xml")
gray = cv.CreateImage((img.width, img.height), 8, 1)
small_img = cv.CreateImage((cv.Round(
img.width / image_scale), cv.Round(img.height / image_scale)), 8, 1)
# convert color input image to grayscale
cv.CvtColor(img, gray, cv.CV_BGR2GRAY)
# scale input image for faster processing
cv.Resize(gray, small_img, cv.CV_INTER_LINEAR)
cv.EqualizeHist(small_img, small_img)
center = (-1, -1, -1)
if (cascade):
t = cv.GetTickCount()
# HaarDetectObjects takes 0.02s
faces = cv.HaarDetectObjects(small_img, cascade,
cv.CreateMemStorage(0), haar_scale,
min_neighbors, haar_flags, min_size)
t = cv.GetTickCount() - t
if faces:
faces.sort()
((x, y, w, h), n) = faces[-1]
# the input to cv.HaarDetectObjects was resized, so scale the
# bounding box of each face and convert it to two CvPoints
pt1 = (int(x * image_scale), int(y * image_scale))
pt2 = (int((x + w) * image_scale), int((y + h) * image_scale))
cv.Rectangle(img, pt1, pt2, cv.RGB(255, 0, 0), 3, 8, 0)
#cv.Rectangle(img, (x,y), (x+w,y+h), 255)
# get the xy corner co-ords, calc the center location
x1 = pt1[0]
x2 = pt2[0]
y1 = pt1[1]
y2 = pt2[1]
centerx = x1 + ((x2 - x1) / 2)
centery = y1 + ((y2 - y1) / 2)
center = (centerx, centery, h * 3)
if cmp(center, (-1, -1, -1)) == 0:
center = None
cv.NamedWindow(WINDOW_NAME, 1)
cv.ShowImage(WINDOW_NAME, img)
if cv.WaitKey(5) == 27:
center = None
return center
def add_features(self, cv_image, face):
""" Look for any new features around the current feature cloud """
""" Create the ROI mask"""
roi = cv.CreateImage(cv.GetSize(cv_image), 8, 1)
""" Begin with all black pixels """
cv.Zero(roi)
""" Get the coordinates and dimensions of the current track box """
try:
((x, y), (w, h), a) = face.track_box
except:
logger.info("Track box has shrunk to zero...")
return
""" Expand the track box to look for new features """
w = int(face.expand_roi * w)
h = int(face.expand_roi * h)
roi_box = ((x, y), (w, h), a)
""" Create a filled white ellipse within the track_box to define the ROI. """
cv.EllipseBox(roi, roi_box, cv.CV_RGB(255, 255, 255), cv.CV_FILLED)
""" Create the temporary scratchpad images """
eig = cv.CreateImage(cv.GetSize(self.grey), 32, 1)
temp = cv.CreateImage(cv.GetSize(self.grey), 32, 1)
if self.feature_type == 0:
""" Get the new features using Good Features to Track """
features = cv.GoodFeaturesToTrack(self.grey,
eig,
temp,
self.max_count,
self.quality,
self.good_feature_distance,
mask=roi,
blockSize=3,
useHarris=0,
k=0.04)
elif self.feature_type == 1:
""" Get the new features using SURF """
features = []
(surf_features, descriptors) = cv.ExtractSURF(
self.grey, roi, cv.CreateMemStorage(0),
(0, self.surf_hessian_quality, 3, 1))
for feature in surf_features:
features.append(feature[0])
""" Append new features to the current list if they are not too
far from the current cluster """
for new_feature in features:
try:
distance = self.distance_to_cluster(new_feature, face.features)
if distance > self.add_feature_distance:
face.features.append(new_feature)
except:
pass
""" Remove duplicate features """
face.features = list(set(face.features))
def _computeConvexHulls(self):
hulls = []
seq = self._contours
while not (seq == None) and len(seq) != 0:
cvxHull = cv.ConvexHull2(seq,
cv.CreateMemStorage(),
return_points=True)
hulls.append(cvxHull)
seq = seq.h_next()
self._convexHulls = hulls
def find_squares_from_binary(gray):
"""
use contour search to find squares in binary image
returns list of numpy arrays containing 4 points
"""
squares = []
storage = cv.CreateMemStorage(0)
contours = cv.FindContours(gray, storage, cv.CV_RETR_TREE,
cv.CV_CHAIN_APPROX_SIMPLE, (0, 0))
storage = cv.CreateMemStorage(0)
while contours:
#approximate contour with accuracy proportional to the contour perimeter
arclength = cv.ArcLength(contours)
polygon = cv.ApproxPoly(contours, storage, cv.CV_POLY_APPROX_DP,
arclength * 0.02, 0)
if is_square(polygon):
squares.append(polygon[0:4])
contours = contours.h_next()
return squares
def main():
hash=hashlib.sha1()
buff=StringIO.StringIO()
buff.write(sys.stdin.read()) #STDIN to buffer
hash.update(buff.getvalue())
buff.seek(0)
pil_im=Image.open(buff)
cv_im = cv.CreateImageHeader(pil_im.size, cv.IPL_DEPTH_8U, 3)
cv.SetData(cv_im, pil_im.tostring())
cascade = cv.Load("../src/main/resources/haarcascade_frontalface_default.xml")
print hash.hexdigest()+":"+str(cv.HaarDetectObjects(cv_im, cascade, cv.CreateMemStorage(0), 1.2, 2, 0, (50, 50)))
def DetectEye(image):
faceCascade = cv.Load("frontalEyes35x16.xml")
min_size = (20, 20)
image_scale = 1
haar_scale = 1.1
min_neighbors = 3
haar_flags = 0
# Allocate the temporary images
grayscale = cv.CreateImage((image.width, image.height), 8, 1)
SmallImage = cv.CreateImage((cv.Round(
image.width / image_scale), cv.Round(image.height / image_scale)), 8,
1)
# Convert input color image to grayscale
cv.CvtColor(image, grayscale, cv.CV_BGR2GRAY)
# Scale input image for faster processing
cv.Resize(grayscale, SmallImage, cv.CV_INTER_LINEAR)
# Equalize the histogram
cv.EqualizeHist(SmallImage, SmallImage)
# Detect the faces
faces = cv.HaarDetectObjects(SmallImage, faceCascade,
cv.CreateMemStorage(0), haar_scale,
min_neighbors, haar_flags, min_size)
# If faces are found
eye = []
if faces:
for ((x, y, w, h), n) in faces:
# The input to cv.HaarDetectObjects was resized, so the stairs
# Bounding box of each face and convert it to two CvPoints
pt1 = (int(x * image_scale), int((y + h / 2) * image_scale))
pt2 = (int((x + w) * image_scale), int((y + h / 2) * image_scale))
eye.append(pt1)
eye.append(pt2)
return eye
def detect_image_faces(image_file, cascade):
# Detect all faces in image:
try:
image = cv.LoadImageM(image_file, cv.CV_LOAD_IMAGE_GRAYSCALE)
faces = cv.HaarDetectObjects( \
image, cascade, cv.CreateMemStorage(0), scale_factor = 1.2, \
min_neighbors = 2, flags = 0, min_size = (20, 20))
except:
faces = []
return faces
def detect(self, cv_im):
import cv
HAAR_CASCADE_PATH = "/usr/local/share/OpenCV/haarcascades/haarcascade_frontalface_default.xml"
cascade = cv.Load(HAAR_CASCADE_PATH)
storage = cv.CreateMemStorage()
faces = []
detected = cv.HaarDetectObjects(cv_im, cascade, storage, 1.2, 2, cv.CV_HAAR_DO_CANNY_PRUNING, (15,15))
if detected:
for (x,y,w,h),n in detected:
faces.append((x,y,w,h))
return faces
def find_characters(grey, bw):
"""Find character contours in a 1-bit image."""
# detect contours
storage = cv.CreateMemStorage()
contour_iter = cv.FindContours(bw, storage, cv.CV_RETR_CCOMP,
cv.CV_CHAIN_APPROX_NONE)
# filter the detected contours
while contour_iter:
contour = Contour(contour_iter, grey)
if contour.valid:
yield contour
contour_iter = contour_iter.h_next()
def getBotCoord():
image = cv.QueryFrame(capture)
imageTreshold = thresholded_image(image, botTreshold[0], botTreshold[1])
current_contour = cv.FindContours(cv.CloneImage(imageTreshold),
cv.CreateMemStorage(), cv.CV_RETR_CCOMP,
cv.CV_CHAIN_APPROX_SIMPLE)
mypos = (0, 0)
if len(current_contour) != 0:
mypos = contourCenter(largestContour(current_contour))
imagehsv = hsv_image(image)
s = cv.Get2D(imagehsv, mypos[0], mypos[1])
return (mypos, s)
def detectFace(image):
storage = cv.CreateMemStorage()
haar = cv.Load(
'/opt/local/share/OpenCV/haarcascades/haarcascade_frontalface_default.xml'
)
detected = cv.HaarDetectObjects(image, haar, storage, 1.2, 2,
cv.CV_HAAR_DO_CANNY_PRUNING, (100, 100))
if detected:
for face in detected:
return face
else:
return False
def __setstate__(self, state):
''' Function required to save and load the state from pickel. '''
# Modeled after SVM pickling
for key, value in state.iteritems():
self.__dict__[key] = value
filename = tempfile.mktemp()
open(filename, 'w').write(self.cascade_data)
self.cascade = cv.Load(filename)
self.storage = cv.CreateMemStorage(0)
os.remove(filename)
def findmouth(img):
# INITIALIZE: loading the classifiers
haarFace = cv.Load(path_to_file + '/haarcascade_frontalface_default.xml')
haarMouth = cv.Load(path_to_file + '/haarcascade_mouth.xml')
# running the classifiers
storage = cv.CreateMemStorage()
detectedFace = cv.HaarDetectObjects(img, haarFace, storage)
detectedMouth = cv.HaarDetectObjects(img, haarMouth, storage)
# FACE: find the largest detected face as detected face
maxFaceSize = 0
maxFace = 0
if detectedFace:
# face: [0][0]: x; [0][1]: y; [0][2]: width; [0][3]: height
for face in detectedFace:
if face[0][3] * face[0][2] > maxFaceSize:
maxFaceSize = face[0][3] * face[0][2]
maxFace = face
if maxFace == 0: # did not detect face
return 2
def mouth_in_lower_face(mouth, face):
# if the mouth is in the lower 2/5 of the face
# and the lower edge of mouth is above that of the face
# and the horizontal center of the mouth is the center of the face
if (mouth[0][1] > face[0][1] + face[0][3] * 3 / float(5)
and mouth[0][1] + mouth[0][3] < face[0][1] + face[0][3]
and abs((mouth[0][0] + mouth[0][2] / float(2)) -
(face[0][0] + face[0][2] / float(2))) <
face[0][2] / float(10)):
return True
else:
return False
# FILTER MOUTH
filteredMouth = []
if detectedMouth:
for mouth in detectedMouth:
if mouth_in_lower_face(mouth, maxFace):
filteredMouth.append(mouth)
maxMouthSize = 0
for mouth in filteredMouth:
if mouth[0][3] * mouth[0][2] > maxMouthSize:
maxMouthSize = mouth[0][3] * mouth[0][2]
maxMouth = mouth
try:
return maxMouth
except UnboundLocalError:
return 2
def get_blobs(bin_arr):
'''
Find all contiguous nonzero blobs in the image, and return a list of Blob objects.
'''
bin_img = cv.fromarray(bin_arr.copy())
storage = cv.CreateMemStorage(0)
contours = cv.FindContours(bin_img, storage, cv.CV_RETR_EXTERNAL, cv.CV_CHAIN_APPROX_NONE)
blobs = []
while contours:
blobs.append(Blob(contours))
contours = contours.h_next()
return sorted(blobs, key=Blob.get_area, reverse=True)
