I'm using the following code to detect certain shapes in an image:
import cv2
import numpy as np
img = cv2.imread("006.jpg")
grey = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(grey,127,255,1)
cv2.imshow('img',thresh)
cv2.waitKey(0)
contours, h = cv2.findContours(thresh, 1, cv2.CHAIN_APPROX_SIMPLE)
contours.sort(key = len)
for contour in contours:
approx = cv2.approxPolyDP(contour, 0.01*cv2.arcLength(contour, True), True)
#star - > yellow
if len(approx) == 10:
cv2.drawContours(img, [contour],0, (0,255,255), -1)
#circle -> black
elif len(approx) >= 11:
cv2.drawContours(img, [contour], 0, (0,0,0), -1)
#triangle -> green
elif len(approx) == 3:
cv2.drawContours(img,[contour],0,(0,255,0),-1)
#square -> blue
elif len(approx) == 4:
cv2.drawContours(img, [contour],0, (255,0,0),-1)
#pentagon -> red
elif len(approx) == 5:
cv2.drawContours(img, [contour],0, (0,0,255), -1)
cv2.imshow('img',img)
cv2.waitKey(0)
This code works well for images on my computer, but when i print out the image, take a picture off it
and try to run the code on it again (as here: image) it doesn't work as well as it should.
I already tried using blurs and canny but I'm not able to smoothen my second picture enough.
I hope someone can help!
Probably using fixed threshold value (127 in your case) it is not a good idea in case of photos taken by a camera (although it works in the abstract case, when the shapes are pure color not influenced by a shade). It seems the 127 is too high value for the image you have provided.
Why don't you try with an Otsu method ? Here's an example of how to use with python in opencv. It will make an threshold level invariant to a real environment you get in case of image taken by a camera.
Related
I have the task of generating data for deep learning. I take seed images, rotate them and plot them randomly on a background. The issue is the rotation results in a broken line boundary around the image and I can't figure out why it appears or how to get rid of it.
def rotateSeed(img):
rotated = imutils.rotate_bound(img, randint(0,360))
for row in range(rotated.shape[0]):
for col in range(rotated.shape[1]):
if (rotated[row,col,0] == 0) and (rotated[row,col,1] == 0) and (rotated[row,col,2] == 0):
rotated[row,col] = default[0,0]
return rotated
Code explanation: default is the background color in the seed image. Rotation produces a black region I cover with the default.
Only one other person has had this problem and the solution does not explain much. It did not even rotate: OpenCV
Original seed image
Rotated seed image
You can use this code for rotation:
import cv2
import numpy as np
img = cv2.imread('C:\\Code\\1.jpeg')
num_rows, num_cols = img.shape[:2]
rotation_matrix = cv2.getRotationMatrix2D((num_cols/2, num_rows/2), 30, 1)
img_rotation = cv2.warpAffine(img, rotation_matrix, (num_cols, num_rows))
cv2.imshow('Rotation', img_rotation)
cv2.waitKey()
I'm trying to detect the upper body using haar cascade.
But still I'm not getting any detection on the image.
import numpy as np
import cv2
cascade = cv2.CascadeClassifier('haarcascade_upperbody.xml');
imgPath = '/home/ayush/Desktop/images.jpeg';
img = cv2.imread(imgPath);
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY);
body = cascade.detectMultiScale(
gray,
scaleFactor = 1.1,
minNeighbors = 5,
minSize = (30,30),
flags = cv2.CASCADE_SCALE_IMAGE
)
for (x, y, w, h) in body:
cv2.rectangle(img, (x, y), (x+w, y+h), (0, 255, 0), 2)
cv2.imshow('Upper Body',img)
cv2.waitKey(0)
cv2.destroyAllWindows()
Why is it so?
I'm using OpenCV3.
It is possible that your scaleFactor is too small. I tried running your code exactly (though with my own image) and found no results at 1.1, but found results at 1.01.
See here for a description of how the parameter affects your results.
That's because the file haarcascade_upperbody.xml is trained to be used with pedestrian detection, and very probably your image is not matching to this case.
Apologies in advance as i am newbie to OpenCV-Python. I set myself a task to create a Passport type image from the video capture.
Using a head and shoulders Haar Cascade i was able to create a portrait photo but i now want to turn the background to a white background (leaving the head and shoulders portrait in the foreground).
Just not sure how/ best way to do this. Any help would be welcome.
Many thanks in advance.
Here is the code:
import numpy as np
import cv2
# face file
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
# eye file
eye_cascade = cv2.CascadeClassifier('haarcascade_eye.xml')
# head shoulders file
hs_cascade = cv2.CascadeClassifier('HS.xml')
cap = cv2.VideoCapture(1)
while 1:
ret, img = cap.read()
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
headshoulders = hs_cascade.detectMultiScale(gray, 1.3, 3)
# find the head and shoulders
for (x,y,w,h) in headshoulders:
# variable change to make portrait orientation
x = int(x*1.5)
w = int(w/1.5)
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
# crop the image
crop_img = img[y: y + h, x: x + w]
# show original and crop
cv2.imshow('crop', crop_img)
cv2.imshow('img', img)
k = cv2.waitKey(30) & 0xff
if k == 27:
break
elif k == ord('s'):
# save out the portrait image
cv2.imwrite('cropimage.png',crop_img)
# release the camera
cap.release()
cv2.destroyAllWindows()
I got it to work. Here is my solution.
PLEASE NOTE: This worked for HI-RES images (Nikon D7100 - JPEG). LOW-RES did NOT work when i tried a Webcam (Logitech C615).
I used some of the code from a link that was suggested.
# import numpy
import numpy as np
# import cv2
import cv2
# import Matplitlib
from matplotlib import pyplot as plt
# Fill any holes function
def get_holes(image, thresh):
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
im_bw = cv2.threshold(gray, thresh, 255, cv2.THRESH_BINARY)[1]
im_bw_inv = cv2.bitwise_not(im_bw)
im_bw_inv, contour, _ = cv2.findContours(im_bw_inv, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
for cnt in contour:
cv2.drawContours(im_bw_inv, [cnt], 0, 255, -1)
nt = cv2.bitwise_not(im_bw)
im_bw_inv = cv2.bitwise_or(im_bw_inv, nt)
return im_bw_inv
# Remove background Function
def remove_background(image, thresh, scale_factor=.25, kernel_range=range(1, 15), border=None):
border = border or kernel_range[-1]
holes = get_holes(image, thresh)
small = cv2.resize(holes, None, fx=scale_factor, fy=scale_factor)
bordered = cv2.copyMakeBorder(small, border, border, border, border, cv2.BORDER_CONSTANT)
for i in kernel_range:
#kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2*i+1, 2*i+1))
kernel = cv2.getStructuringElement(cv2.MORPH_CROSS, (2*i+1, 2*i+1))
bordered = cv2.morphologyEx(bordered, cv2.MORPH_CLOSE, kernel)
unbordered = bordered[border: -border, border: -border]
mask = cv2.resize(unbordered, (image.shape[1], image.shape[0]))
fg = cv2.bitwise_and(image, image, mask=mask)
return fg
# Load a color image in grayscale
img = cv2.imread('original/11.png')
# Start background removal -- Parameters are <image> and <threshold level>
nb_img = remove_background(img, 180)
# Change Black Pixels to WHITE
nb_img[np.where((nb_img==[0,0,0]).all(axis=2))] = [255,255,255]
# resize the viewing size (as the images are too big for the screen
small = cv2.resize(nb_img, (300, 400))
# Show the finished image
cv2.imshow('image',small)
k = cv2.waitKey(0) & 0xFF
if k == 27: #wait for ESC key to exit
# if ESC pressed close the camera windows
cv2.destroyAllWindows()
elif k == ord('s'): #wait for 's' key to save and exit
# Save the img(greyscale version)
cv2.imwrite('bg_removal/11.png',small)
cv2.destroyAllWindows()
I want to find the HSV value of a LASER dot using opencv and python. I got the code http://opencv-srf.blogspot.com.au/2010/09/object-detection-using-color-seperation.html from here but it is in c++, installing visual studio and opencv takes time so i changed the code in python
import cv2
import numpy as np
def callback(x):
pass
cap = cv2.VideoCapture(0)
cv2.namedWindow('image')
ilowH = 0
ihighH = 179
ilowS = 0
ihighS = 255
ilowV = 0
ihighV = 255
# create trackbars for color change
cv2.createTrackbar('lowH','image',ilowH,179,callback)
cv2.createTrackbar('highH','image',ihighH,179,callback)
cv2.createTrackbar('lowS','image',ilowS,255,callback)
cv2.createTrackbar('highS','image',ihighS,255,callback)
cv2.createTrackbar('lowV','image',ilowV,255,callback)
cv2.createTrackbar('highV','image',ihighV,255,callback)
while(1):
ret, frame = cap.read()
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
cv2.imshow('hsv', hsv)
lower_hsv = np.array([ilowH, ilowS, ilowV])
higher_hsv = np.array([ihighH, ihighS, ihighV])
mask = cv2.inRange(hsv, lower_hsv, higher_hsv)
cv2.imshow('mask', mask)
cv2.imshow('frame', frame)
print ilowH, ilowS, ilowV
if(cv2.waitKey(1) & 0xFF == ord('q')):
break
cv2.destroyAllWindows()
cap.release()
but this code doesnot threshold anything. It seems like the trackbars i created doesnot change the value of ilowH ,ilowS, ilowV . I checked it by printing those values inside while loop. What could be the problem for not thresholding any of those values or is there better code in python to find HSV values of the LASER.
Thank you, any help is appreciated.
You can grab the trackbar values with cv2.getTrackbarPos(). Also note that sometimes it puts trackbars out of order, which is annoying, but at least they're labeled.
However, I don't think that these trackbars will work very well for live video feed. There's a lot of freezing issues. You'll have to have a super low framerate (works for me with cv2.waitKey(500) if you're actually trying to display it). This is mostly due to the trackbars sucking, not the thresholding operation, which is not that slow.
You need to add your trackbars after you create the named window. Then, for your while loop, try:
while True:
# grab the frame
ret, frame = cap.read()
# get trackbar positions
ilowH = cv2.getTrackbarPos('lowH', 'image')
ihighH = cv2.getTrackbarPos('highH', 'image')
ilowS = cv2.getTrackbarPos('lowS', 'image')
ihighS = cv2.getTrackbarPos('highS', 'image')
ilowV = cv2.getTrackbarPos('lowV', 'image')
ihighV = cv2.getTrackbarPos('highV', 'image')
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
lower_hsv = np.array([ilowH, ilowS, ilowV])
higher_hsv = np.array([ihighH, ihighS, ihighV])
mask = cv2.inRange(hsv, lower_hsv, higher_hsv)
frame = cv2.bitwise_and(frame, frame, mask=mask)
# show thresholded image
cv2.imshow('image', frame)
k = cv2.waitKey(1000) & 0xFF # large wait time to remove freezing
if k == 113 or k == 27:
break
and finally end the file with a cv2.destroyAllWindows()
As an aside, the maximum H value for HSV is 180, not 179.
Shameless plug: I happened to just finish a project doing precisely this, but on images. You can grab it on GitHub here. There is an example; try running it and then modifying as you need. It will let you change the colorspace and threshold inside each different colorspace, and it will print the final thresholding values that you ended on. Additionally it will return the output image from the operation for you to use, too. Hopefully it is useful for you! Feel free to send any issues or suggestions through GitHub for the project.
Here is an example of it running:
And as output it gives you:
Colorspace: HSV
Lower bound: [68.4, 0.0, 0.0]
Upper bound: [180.0, 255.0, 255.0]
as well as the binary image. I am currently working on getting this into a web application as well, but that probably won't be finished for a few days.
Use this code to find range of masking of real-time video! this might save you time. Below is a whole code, Check it and run it to have a test.
import cv2
import numpy as np
camera = cv2.VideoCapture(0)
def nothing(x):
pass
cv2.namedWindow('marking')
cv2.createTrackbar('H Lower','marking',0,179,nothing)
cv2.createTrackbar('H Higher','marking',179,179,nothing)
cv2.createTrackbar('S Lower','marking',0,255,nothing)
cv2.createTrackbar('S Higher','marking',255,255,nothing)
cv2.createTrackbar('V Lower','marking',0,255,nothing)
cv2.createTrackbar('V Higher','marking',255,255,nothing)
while(1):
_,img = camera.read()
img = cv2.flip(img,1)
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
hL = cv2.getTrackbarPos('H Lower','marking')
hH = cv2.getTrackbarPos('H Higher','marking')
sL = cv2.getTrackbarPos('S Lower','marking')
sH = cv2.getTrackbarPos('S Higher','marking')
vL = cv2.getTrackbarPos('V Lower','marking')
vH = cv2.getTrackbarPos('V Higher','marking')
LowerRegion = np.array([hL,sL,vL],np.uint8)
upperRegion = np.array([hH,sH,vH],np.uint8)
redObject = cv2.inRange(hsv,LowerRegion,upperRegion)
kernal = np.ones((1,1),"uint8")
red = cv2.morphologyEx(redObject,cv2.MORPH_OPEN,kernal)
red = cv2.dilate(red,kernal,iterations=1)
res1=cv2.bitwise_and(img, img, mask = red)
cv2.imshow("Masking ",res1)
if cv2.waitKey(10) & 0xFF == ord('q'):
camera.release()
cv2.destroyAllWindows()
break`
Thanks!
Hugs..
I want to extract only the rectangular part of the mouth detected by my code how can I do it:
import numpy as np
import cv2
face_cascade = cv2.CascadeClassifier('/usr/local/share/OpenCV/haarcascades/haarcascade_frontalface_default.xml')
mouth_cascade = cv2.CascadeClassifier('/usr/local/share/OpenCV/haarcascades/haarcascade_smile.xml')
img = cv2.imread('Images/image_0033.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x,y,w,h) in faces:
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
roi_gray = gray[y:y+h, x:x+w]
roi_color = img[y:y+h, x:x+w]
mouth = mouth_cascade.detectMultiScale(roi_gray,2.0,25)
for (ex,ey,ew,eh) in mouth:
cv2.rectangle(roi_color,(ex,ey),(ex+ew,ey+eh),(0,255,0),3)
cv2.imshow('img',nwimg)
cv2.waitKey(0)
cv2.destroyAllWindows()
As seen in the code I just want to extract the rectangular mouth region I have used commands like var = img[y:y+h,x:x+w] but this has not worked.
It is simple, replace this line:
cv2.rectangle(roi_color,(ex,ey),(ex+ew,ey+eh),(0,255,0),3) with
cv2.rectangle(img,(ex,ey),(ex+ew,ey+eh),(0,255,0),3)
and display the following:
cv2.imshow('Detected Mouth',img)
In this way you will draw a rectangle over the mouth.
EDIT
You can crop your region of interest (in this case the mouth) using numpy operation as follows:
crop_img = img[ey:ey+eh, ex:ex+ew]
cv2.imshow('Cropped Mouth',crop_img)
This is what I got:
Sample 1:
Sample 2: