def thresholding(x):
global thres, value, maxValue, img, tipo
imgO = img
if (x == 0):
thres = None
filtro = img
value = 0
maxValue = 255
cv2.createTrackbar('Value', windowTitle, value, maxValue, fValue)
cv2.createTrackbar('MaxValue', windowTitle, maxValue, maxValue, fMaxValue)
elif (x == 1):
thres = cv2.THRESH_BINARY+cv2.THRESH_OTSU
elif (x==2):
thres = cv2.THRESH_BINARY+cv2.THRESH_OTSU
img = cv2.GaussianBlur(img,(5,5),0)
if (x != 0):
ret, filtro = cv2.threshold(img,value, maxValue, thres)
tipo = x
img = imgO
blobImg = Image(filtro)
invImg = blobImg.invert()
blobImg = blobImg.rotate90()
invImg = blobImg.invert()
blobs = invImg.findBlobs()
for blob in blobs:
#print blob.coordinates()
invImg.dl().circle(blob.coordinates(), 3, Color.RED, filled = True)
blobImg.addDrawingLayer(invImg.dl())
blobs.show(color=Color.GREEN,width=1)
cv2.imshow(windowTitle, filtro)
def adaptative_thresholding(x):
global thres, na, cons, maxValue, tipo, img, windoTitle
if x == 0:
thres = img
maxValue = 255
na = 11
cons = 2;
cv2.createTrackbar('Neighbourhood area (odds)', windowTitle, na, maxValue, fneighbourdhood_area)
cv2.createTrackbar('Constant', windowTitle, -maxValue, maxValue, fConstant)
cv2.createTrackbar('MaxValue', windowTitle, maxValue, maxValue, fMaxValue)
elif x == 1:
thres = cv2.adaptiveThreshold(img, maxValue,cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY, na, cons)
elif x == 2:
thres = cv2.adaptiveThreshold(img, maxValue, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY,na,cons)
tipo = x
blobImg = Image(thres)
invImg = blobImg.invert()
blobImg = blobImg.rotate90()
invImg = blobImg.invert()
blobs = invImg.findBlobs()
for blob in blobs:
#print blob.coordinates()
invImg.dl().circle(blob.coordinates(), 3, Color.RED, filled = True)
blobImg.addDrawingLayer(invImg.dl())
blobs.show(color=Color.GREEN,width=1)
cv2.imshow(windowTitle, thres)
def fneighbourdhood_area(x):
global na, thres, windowTitle, tipo
if x % 2 ==0:
na = x+1
else:
na = x
if na == 0 or na == 1:
na = 3
if tipo == 0:
thres = img
elif tipo == 1:
thres = cv2.adaptiveThreshold(img, maxValue,cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY, na, cons)
elif tipo == 2:
thres = cv2.adaptiveThreshold(img, maxValue, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY,na,cons)
blobImg = Image(thres)
invImg = blobImg.invert()
blobImg = blobImg.rotate90()
invImg = blobImg.invert()
blobs = invImg.findBlobs()
for blob in blobs:
#print blob.coordinates()
invImg.dl().circle(blob.coordinates(), 3, Color.RED, filled = True)
blobImg.addDrawingLayer(invImg.dl())
blobs.show(color=Color.GREEN,width=1)
cv2.imshow(windowTitle, thres)
def getConvolvedImage(self, kern, rep, bias):
''' Return a simple cv compatiable 8bit greyscaled image that has had
the specified kernel applied rep times with bias supplied'''
conv = ds.convolveColourMap(kern, rep, bias)
iE = Image(conv.transpose())
return iE.invert()
def getDepth(self):
''' Return a simple cv compatiable 8bit depth image '''
depth = ds.getDepthMap()
np.clip(depth, 0, 2**10 - 1, depth)
depth >>= 2
depth = depth.astype(np.uint8)
iD = Image(depth.transpose())
return iD.invert()
def getDepth(self):
''' Return a simple cv compatiable 8bit depth image '''
depth = ds.getDepthMap()
np.clip(depth, 0, 2**10 - 1, depth)
depth >>=2
depth = depth.astype(np.uint8)
iD = Image(depth.transpose())
return iD.invert()
def fMaxValue(x):
global maxValue, value, thres, img, filtro
maxValue = x
if (thres is None):
filtro = img
else:
ret, filtro = cv2.threshold(img,value, maxValue, thres)
blobImg = Image(filtro)
invImg = blobImg.invert()
blobImg = blobImg.rotate90()
invImg = blobImg.invert()
blobs = invImg.findBlobs()
for blob in blobs:
#print blob.coordinates()
invImg.dl().circle(blob.coordinates(), 3, Color.RED, filled = True)
blobImg.addDrawingLayer(invImg.dl())
blobs.show(color=Color.GREEN,width=1)
cv2.imshow(windowTitle, filtro)
def getConvolvedDepth(self, kern, rep, bias):
''' Return a simple cv compatiable 8bit depth map that has had
the specified kernel applied rep times '''
conv = ds.convolveDepthMap(kern, rep, bias)
np.clip(conv, 0, 2**10 - 1, conv)
conv >>=2
conv = conv.astype(np.uint8)
iE = Image(conv.transpose())
return iE.invert()
def fMaxValue(x):
global maxValueAdaptative, windowTitle, thresAdaptative, img, naAdaptative, consAdaptative, filtro
maxValueAdaptative = x
if tipoAdaptative == 0:
thresAdaptative = img
elif tipoAdaptative == 1:
thresAdaptative = cv2.adaptiveThreshold(filtro, maxValueAdaptative,cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY, naAdaptative, consAdaptative)
elif tipoAdaptative == 2:
thresAdaptative = cv2.adaptiveThreshold(filtro, maxValueAdaptative, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY,naAdaptative,consAdaptative)
blobImg = Image(thresAdaptative)
invImg = blobImg.invert()
blobImg = blobImg.rotate90()
invImg = blobImg.invert()
blobs = invImg.findBlobs()
for blob in blobs:
#print blob.coordinates()
invImg.dl().circle(blob.coordinates(), 3, Color.RED, filled = True)
blobImg.addDrawingLayer(invImg.dl())
blobs.show(color=Color.GREEN,width=1)
cv2.imshow(windowTitle, thresAdaptative)
def fConstant(x):
global cons, thres, windowTitle, tipo, maxValue, na, img
# const positive to white, otherwise, to black
cons = x
if tipo == 0:
thres = img
elif tipo == 1:
thres = cv2.adaptiveThreshold(img, maxValue,cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY, na, cons)
elif tipo == 2:
thres = cv2.adaptiveThreshold(img, maxValue, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY,na,cons)
blobImg = Image(thres)
invImg = blobImg.invert()
blobImg = blobImg.rotate90()
invImg = blobImg.invert()
blobs = invImg.findBlobs()
for blob in blobs:
#print blob.coordinates()
invImg.dl().circle(blob.coordinates(), 3, Color.RED, filled = True)
blobImg.addDrawingLayer(invImg.dl())
blobs.show(color=Color.GREEN,width=1)
cv2.imshow(windowTitle, thres)
def thresholding(x):
global thres, value, maxValue, img, filtro
if (x == 0):
thres = None
filtro = img
value = 127
maxValue = 255
cv2.createTrackbar('Value', windowThres, value, maxValue, fValue)
cv2.createTrackbar('MaxValue', windowThres, maxValue, maxValue, fMaxValue)
elif (x == 1):
thres = cv2.THRESH_BINARY
elif (x==2):
thres = cv2.THRESH_BINARY_INV
elif (x==3):
thres = cv2.THRESH_TRUNC
elif (x==4):
thres = cv2.THRESH_TOZERO
elif (x==5):
thres = cv2.THRESH_TOZERO_INV
if (x != 0):
ret, filtro = cv2.threshold(img,value, maxValue, thres)
blobImg = Image(filtro)
invImg = blobImg.invert()
blobImg = blobImg.rotate90()
invImg = blobImg.invert()
blobs = invImg.findBlobs()
for blob in blobs:
#print blob.coordinates()
invImg.dl().circle(blob.coordinates(), 3, Color.RED, filled = True)
blobImg.addDrawingLayer(invImg.dl())
blobs.show(color=Color.GREEN,width=1)
cv2.imshow(windowTitle, filtro)
def process_image(image_url):
# Print the url for image that is being processed.
print "Processing image: {}".format(image_url)
# Construct the Image object from the image URL
img = Image(image_url)
# Find the coin blobs from the image after inverting the image
coins = img.invert().findBlobs(minsize=500)
# Use a quarter to calibrate the largest coin in the coin blobs.
# Logic:
# coin_diameter_values[3,0] is the size of the US Mint Quarter.
# Find the largest radius of all the coins in the image. This will be our reference Quarter.
# usmint_quarter/radius_of_our_quarter will provide the calibration factor.
# In other words: convert pixels to millimeter.
px2mm = coin_diameter_values[3, 0] / max([c.radius() * 2 for c in coins])
# Initialize index & total value
i = 0
value = 0.0
# For each blob in the coins blob list
for c in coins:
i = i + 1
# Find the diameter of this coin blob & normalize to the calibration factor
# ie., find the diameter in millimeter of this coin.
diameter_in_mm = c.radius() * 2 * px2mm
# Get an array of values for difference between this coin and all the US Mint coins.
distance = np.abs(diameter_in_mm - coin_diameter_values[:, 0])
#print "Coin diameter: " , diameter_in_mm, " Distance: ", distance
# Find the coin with the smallest difference. This is our best guess on the coin type.
index = np.where(distance == np.min(distance))[0][0]
# Get the value of the coin and add it to the total amount
coinValue = coin_diameter_values[index, 1]
value += coinValue
#coinImg = c.crop()
#coinImg.drawText(str(coinValue))
#coinImg.save("Results/coin"+str(i)+".png")
message = "The total value of the coins in the image is ${0}".format(value)
print message
return "{}".format(value)
def get_pan_info(img_path):
if img_path == None:
img_path = sys.argv[1]
print "Reading from file: " + img_path
img = Image(img_path).toRGB()
min_pan_area = img.width * img.height / 10
pan_rects = img.invert().findBlobs((25, 0, 0), min_pan_area)
if pan_rects and len(pan_rects) > 0:
img = img.crop(pan_rects[0])
if img.width < 350 or img.height < 200:
print "Error too small PAN image"
exit(1)
cropped_img = img.crop(0, img.height / 4.60, img.width / 1.4,
img.height / 4 * 2.3)
if cropped_img.width < 550:
cropped_img = cropped_img.resize(
550, 550 * cropped_img.height / cropped_img.width)
t_img = cropped_img.threshold(100)
img_text = pytesseract.image_to_string(t_img.getPIL(), lang='eng')
context = {}
learn_text(context, img_text)
t_img = cropped_img
img_text = pytesseract.image_to_string(t_img.getPIL(), lang='eng')
learn_text(context, img_text)
t_img = cropped_img.threshold(90)
img_text = pytesseract.image_to_string(t_img.getPIL(), lang='eng')
learn_text(context, img_text)
t_img = cropped_img.threshold(110)
img_text = pytesseract.image_to_string(t_img.getPIL(), lang='eng')
learn_text(context, img_text)
#print context['best_list']
pan_info = get_fields(context['best_list'])
#print json.dumps(pan_info, indent=2)
return pan_info
from SimpleCV import Camera, Image,Color
import time
'''exemplo que carrega uma imagem totalmente vermelha e substiui o fundo do rotate
que e sempre preto por vermelho'''
cam = Camera(1)
img = cam.getImage()
vermelho = Image('/home/administrador-x/vermelho.png').resize(img.width,img.height)
rotate = img.rotate(-65)
mask = rotate.hueDistance(color=Color.BLACK,minsaturation=1,minvalue=1).erode(3).binarize(254)
img2 = mask+vermelho.invert()
img3 = img2.invert()+rotate
img3.show()
time.sleep(5)
from SimpleCV import Image, Blob
import numpy as np
img = Image("coins.jpg")
coins = img.invert().findBlobs(minsize=500)
value = 0.0
# The value of the coins in order of their size
# http://www.usmint.gov/about_the_mint/?action=coin_specifications
coin_diameter_values = np.array([[19.05, 0.10], [21.21, 0.01], [17.91, 0.05],
[24.26, 0.25]])
# Use a quarter to calibrate (in this example we must have one)
px2mm = coin_diameter_values[3, 0] / max([c.radius() * 2 for c in coins])
for c in coins:
diameter_in_mm = c.radius() * 2 * px2mm
distance = np.abs(diameter_in_mm - coin_diameter_values[:, 0])
index = np.where(distance == np.min(distance))[0][0]
value += coin_diameter_values[index, 1]
print "The total value of the coins is $", value
from SimpleCV import Camera, Image, Color
import time
'''exemplo que carrega uma imagem totalmente vermelha e substiui o fundo do rotate
que e sempre preto por vermelho'''
cam = Camera(1)
img = cam.getImage()
vermelho = Image('/home/administrador-x/vermelho.png').resize(
img.width, img.height)
rotate = img.rotate(-65)
mask = rotate.hueDistance(color=Color.BLACK, minsaturation=1,
minvalue=1).erode(3).binarize(254)
img2 = mask + vermelho.invert()
img3 = img2.invert() + rotate
img3.show()
time.sleep(5)
# -*- coding: cp1252 -*-
from SimpleCV import Camera,Image,Display
from math import *
display=Display()
cam=Camera()
sung=Image("E:/sung2.png")
sung2=Image("E:/RAY-BAN-Mens-Unisex-Designer-Genuine-Sunglasses-Aviator-RayBan-RB-4180-RRP-£165-For-Sale-at-UsedLux.com-Preowned-Used-designer-clothing-in-London-3-182103112013w.jpg")
sung2=sung2.invert()
sungar=[sung,sung2]
i=0
img3=sungar[i]
while display.isNotDone:
img=cam.getImage()
faces=img.findHaarFeatures('face.xml')
if faces is not None:
faces=faces.sortArea()
bigface=faces[-1]
bigeye=img.findHaarFeatures('two_eyes_big.xml')
if(bigeye is not None):
bigeye=bigeye.sortArea()
bigeye=bigeye[-1]
print "yo"
lefteye=img.findHaarFeatures('lefteye.xml')
righteye=img.findHaarFeatures('right_eye.xml')
if lefteye is not None and righteye is not None:
if bigeye is not None:
a=int((bigeye.width()))
b=int((bigeye.height()))
print a,b
sungar[i]=sungar[i].resize(a+20,b+15)
if bigeye is not None:
