Related
I am doing contour detection on a chroma key corrected image. Everything works fine when I filter out just the blues, but when I try to get a better chroma correction by also filtering the reds, suddenly my contours cannot be detected anymore. Anyone any suggestions?
WITH BLUE FILTER:
img = cv2.imread('yellowcropped.jpg', 1)
lower_blue = np.array([0, 0, 15]) ##[R value, G value, B value]
upper_blue = np.array([255, 255, 60])
mask = cv2.inRange(image_copy, lower_blue, upper_blue)
WITH BLUE AND RED FILTER:
lower_blue = np.array([180, 0, 15]) ##[R value, G value, B value]
upper_blue = np.array([255, 255, 60])
(notice the top left image get's much crisper, but NO CONTOURS are detected anymore.)
BELOW MY CONTOUR FINDING CODE:
imgContour = image_original.copy()
imgBlur = cv2.GaussianBlur(img, (7, 7), 1)
imgGray = imgBlur
imgCanny = cv2.Canny(imgGray,threshold1,threshold2)
kernel = np.ones((5, 5))
imgDil = cv2.dilate(imgCanny, kernel, iterations=1)
getContours(imgDil,imgContour)
def getContours(img,imgContour):
""" DRAWS AND FINDS CONTOURS, THEN RETURNS a list of lists incl x0, y0, w, h"""
contour_list = []
contours, hierarchy = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
# print('contours:', contours)
for cnt in contours:
area = cv2.contourArea(cnt)
areaMin = cv2.getTrackbarPos("Area", "Parameters")
if area > areaMin and area < 5000:
cv2.drawContours(imgContour, cnt, -1, (255, 0, 0), 7)
peri = cv2.arcLength(cnt, True)
approx = cv2.approxPolyDP(cnt, 0.02 * peri, True)
# print(len(approx))
x , y , w, h = cv2.boundingRect(approx)
print('contour bounding:', x,y,w,h)
center_x = int(x + w/2)
center_y = int(y + h/2)
cv2.circle(imgContour,(center_x, center_y), 5, (0, 0, 255), 5)
cv2.rectangle(imgContour, (x , y ), (x + w , y + h ), (0, 255, 0), 5)
cv2.putText(imgContour, "Points: " + str(len(approx)), (x + w + 20, y + 20), cv2.FONT_HERSHEY_COMPLEX, .7,
(0, 255, 0), 2)
cv2.putText(imgContour, "Area: " + str(int(area)), (x + w + 20, y + 45), cv2.FONT_HERSHEY_COMPLEX, 0.7,
(0, 255, 0), 2)
if area < 3500:
cv2.putText(imgContour, "THIS IS A SMALL PART" , (x + w + 20, y + 70), cv2.FONT_HERSHEY_COMPLEX, 0.7,
(0, 255, 0), 2)
contour_list.append([x,y,w,h])
return contour_listenter code here
So i still do not entirely know what went wrong here but I found a solution for anyone in the future looking to first chroma key correct (Remove background) and then do contour detection:
I dropped the gaussian filter, dilate and canny and instead just inverted the image's colours (contour detection only detects white parts on black background) using:
mask = cv2.bitwise_not(mask)
I then changed the contour detection from cv2.RETR_EXTERNAL to cv2.RETR_LIST
Somehow that fixed it, the result is now really good.
In this image I am trying to detect horizontal lines. The code works well when image is not skewed. However, it is not working on such skewed images. I have tried this method to detect the right angle by histogram but many times is actually making it more skewed - python-opencv-skew-correction-for-ocr
Below is code to detect horizontal lines:
gray=cv2.cvtColor(img_final_bin,cv2.COLOR_BGR2GRAY)
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (100,1))
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
detected_lines = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)
cnts, hierarchy = cv2.findContours(detected_lines, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
boundingBoxes = [list(cv2.boundingRect(c)) for c in cnts]
Below is the code for skew correction, which is giving wrong results to me:
def correct_skew(image, delta=0.001, limit=3):
def determine_score(arr, angle):
data = inter.rotate(arr, angle, reshape=False, order=0)
histogram = np.sum(data, axis=1)
score = np.sum((histogram[1:] - histogram[:-1]) ** 2)
return histogram, score
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
print("thresh", thresh.shape)
thresh1 = thresh[0:500, 0:500]
print("thresh1", thresh1.shape)
scores = []
angles = np.arange(-limit, limit + delta, delta)
for i, angle in enumerate(angles):
histogram, score = determine_score(thresh1, angle)
scores.append(score)
# if i%100 == 0:
# print(score, angle, len(angles), i)
best_angle = angles[scores.index(max(scores))]
(h, w) = image.shape[:2]
center = (w // 2, h // 2)
M = cv2.getRotationMatrix2D(center, best_angle, 1.0)
rotated = cv2.warpAffine(image, M, (w, h), flags=cv2.INTER_CUBIC, \
borderMode=cv2.BORDER_REPLICATE)
return best_angle, rotated
Python Wand, which is based upon ImageMagick has a deskew function.
Input:
from wand.image import Image
from wand.display import display
with Image(filename='table.png') as img:
img.deskew(0.4*img.quantum_range)
img.save(filename='table_deskew.png')
display(img)
Result:
I want to extract some rectangles at the top from a UML sequence diagram in jpg format by using OpenCV.
The algorithm I use finds way too many rectangles that are super small and not needed.
I think the mess up is somewhere in the beginning of the code where I apply canny edge detection but I am not sure.
I want to capture only the big rectangles from the top and center.
Thanks for any help.
import cv2
import numpy as np
import imutils
image = cv2.imread("./diagrams/sd2.jpg")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray, 90, 150, 3)
cnts = cv2.findContours(edges, cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if imutils.is_cv2() else cnts[1]
cv2.drawContours(image, cnts, -1, (0, 255, 0), 1)
def detect(c):
shape = "unidentified"
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.03 * peri, True)
if len(approx) == 4:
(x, y, w, h) = cv2.boundingRect(approx)
ar = w / float(h)
shape = "square" if ar >= 0.95 and ar <= 1.05 else "rectangle"
return shape
# loop over the contours
for c in cnts:
M = cv2.moments(c)
if M["m00"] != 0:
cX = int((M["m10"] / M["m00"]))
cY = int((M["m01"] / M["m00"]))
shape = detect(c)
c = c.astype("float")
c = c.astype("int")
if(shape == "rectangle"):
cv2.drawContours(image, [c], -1, (0, 255, 0), 2)
cv2.putText(image, shape, (cX, cY), cv2.FONT_HERSHEY_SIMPLEX,
0.5, (0, 0, 0), 2)
# show the output image
cv2.imshow("Image", image)
cv2.waitKey(0)
I am trying to detect edges from the products on a shelf using histogram projections. But I am stuck at 2 levels.
The challenges that I m facing are:
How to get the longest non shelf segment from the image i.e Detect the width of the widest product on the shelf from the available one.
How to achieve morphological reconstruction using custom markers.To eliminate
all small horizontal segments, I am generating 2 markers which can be seen in 'markers.png' (Attached). With them, I am calculating the minimum of the reconstruction outputs from both the markers.
Need assistance on this.
Thanks a lot
Below is my python code for the same.
Below is my python code
********************************************************************************
import numpy as np
import cv2 as cv
from matplotlib import pyplot as plt
import math
# Read the input image
img = cv.imread('C:\\Users\\672059\\Desktop\\p2.png')
# Converting from BGR to RGB. Default is BGR.
# img_rgb = cv.cvtColor(img, cv.COLOR_BGR2RGB)
# Resize the image to 150,150
img_resize = cv.resize(img, (150, 150))
# Get the dimensions of the image
img_h, img_w, img_c = img_resize.shape
# Split the image on channels
red = img[:, :, 0]
green = img[:, :, 1]
blue = img[:, :, 2]
# Defining a vse for erosion
vse = np.ones((img_h, img_w), dtype=np.uint8)
# Morphological Erosion for red channel
red_erode = cv.erode(red, vse, iterations=1)
grad_red = cv.subtract(red, red_erode)
# Morphological Erosion for green channel
green_erode = cv.erode(green, vse, iterations=1)
grad_green = cv.subtract(green, green_erode)
# Morphological Erosion for blue channel
blue_erode = cv.erode(blue, vse, iterations=1)
grad_blue = cv.subtract(blue, blue_erode)
# Stacking the individual channels into one processed image
grad = [grad_red, grad_green, grad_blue]
retrieved_img = np.stack(grad, axis=-1)
retrieved_img = retrieved_img.astype(np.uint8)
retrieved_img_gray = cv.cvtColor(retrieved_img, cv.COLOR_RGB2GRAY)
plt.title('Figure 1')
plt.imshow(cv.bitwise_not(retrieved_img_gray), cmap=plt.get_cmap('gray'))
plt.show()
# Hough Transform of the image to get the longest non shelf boundary from the image!
edges = cv.Canny(retrieved_img_gray, 127, 255)
minLineLength = img_w
maxLineGap = 10
lines = cv.HoughLinesP(edges, 1, np.pi/180, 127, minLineLength=1, maxLineGap=1)
temp = img.copy()
l = []
for x in range(0, len(lines)):
for x1, y1, x2, y2 in lines[x]:
cv.line(temp, (x1, y1), (x2, y2), (0, 255, 0), 2)
d = math.sqrt((x2-x1)**2 + (y2-y1)**2)
l.append(d)
# Defining a hse for erosion
hse = np.ones((1, 7), dtype=np.uint8)
opening = cv.morphologyEx(retrieved_img_gray, cv.MORPH_OPEN, hse)
plt.title('Figure 2')
plt.subplot(1, 2, 1), plt.imshow(img)
plt.subplot(1, 2, 2), plt.imshow(cv.bitwise_not(opening), 'gray')
plt.show()
# Dilation with disk shaped structuring element
horizontal_size = 7
horizontalstructure = cv.getStructuringElement(cv.MORPH_ELLIPSE, (horizontal_size, 1))
dilation = cv.dilate(opening, horizontalstructure)
plt.title('Figure 3')
plt.imshow(cv.bitwise_not(dilation), 'gray')
plt.show()
# Doing canny edge on dilated image
edge = cv.Canny(dilation, 127, 255)
plt.title('Figure 4')
plt.imshow(edges, cmap='gray')
plt.show()
h_projection = edge.sum(axis=1)
print(h_projection)
plt.title('Projection')
plt.plot(h_projection)
plt.show()
listing = []
for i in range(1, len(h_projection)-1):
if h_projection[i-1] == 0 and h_projection[i] == 0:
listing.append(dilation[i])
listing.append(dilation[i-1])
a = np.array([np.array(b) for b in l])
h = len(l)
_, contours, _ = cv.findContours(a, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE)
x, y, w, h = cv.boundingRect(contours[0])
y = y + i - h
cv.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)
l.clear()
plt.imshow(img)
plt.show()
# Generating a mask
black_bg = np.ones([img_h, img_w], dtype=np.uint8)
# Clone the black bgd image
left = black_bg.copy()
right = black_bg.copy()
# Taking 10% of the image width
ten = int(0.1 * img_w)
left[:, 0:ten+1] = 0
right[:, img_w-ten:img_w+1] = 0
plt.title('Figure 4')
plt.subplot(121), plt.imshow(left, 'gray')
plt.subplot(122), plt.imshow(right, 'gray')
plt.show()
# Marker = left and right. Mask = dilation
mask = dilation
marker_left = left
marker_right = right
********************************************************************************
markers.png link: https://i.stack.imgur.com/45WJ6.png
********************************************************************************
Based on you input image, I would :
take a picture of an empty fridge
then compare the current image with the empty one.
play with morphological operations
get connected components > size N
If you can't take a empty fridge image:
segment the shelves (threshold white parts)
undo do the rotation of the image by using image moments of the shelves
for each shelve:
Threshold on saturation
Do a vertical projection
Count maxima.
Tresholded:
Erode-dilate:
Connected componens (width > 10 * height + > minsize):
And you have shelves.
Now take the average Y form each shelf and cut the original image in pieces:
Dither to 8 colors:
and threshold:
Connected components (h>1.5*w, minsize... this is hard here, I played with it :)
I have performed preprocessing steps in an noisy acoustic image and now I need to detect narrow black lines.
Can you think of a better way to detect these lines?
My goal is to detect the line in the red box in this image.
Failed Answer: - This is not a perfect solution but will require further work to make it robust for various images. I noticed that there is very less noise in the black lines, and thus Canny does not found a lot of edges within this region. Code and results below:-
import numpy as np
import cv2
gray = cv2.imread('2.png')
edges = cv2.Canny(gray,10,60,apertureSize = 7)
cv2.imwrite('2-1-edges-10-60.jpg',edges)
kernel = np.ones((5,5),np.uint8)
closeEdges = cv2.morphologyEx(edges, cv2.MORPH_CLOSE, kernel)
cv2.imwrite('2-2-edges-10-60-dilated-1.jpg',closeEdges)
invertEdges = 255 - closeEdges
cv2.imwrite('2-3-invertedges-10-60.jpg',invertEdges)
minLineLength=100
lines = cv2.HoughLinesP(image=invertEdges,rho=1,theta=np.pi/180, threshold=200,lines=np.array([]), minLineLength=minLineLength,maxLineGap=80)
a,b,c = lines.shape
for i in range(a):
cv2.line(gray, (lines[i][0][0], lines[i][0][1]), (lines[i][0][2], lines[i][0][3]), (0, 0, 255), 1, cv2.LINE_AA)
cv2.imwrite('2-4-houghlines.jpg',gray)
Using connected component on inverse of output image and finding maximum size elements could be helpful.
Another way of approaching this is use of gradient image and directly finding area of small range of gradient magnitude. This approach would be much more flexible as it will not require using fixed threshold values - 10 and 60 as above. Threshold values can be adaptive according to image gradient/you can normalize gradient of image before using hard-coded thresholds.
Better Answer(30-40% accurate)
import numpy as np
import cv2
import os
# Store all images in this folder
path='images-1'
def autocrop(image, threshold=0):
if len(image.shape) == 3:
flatImage = np.max(image, 2)
else:
flatImage = image
rows = np.where(np.max(flatImage, 0) > threshold)[0]
if rows.size:
cols = np.where(np.max(flatImage, 1) > threshold)[0]
image = image[cols[0]: cols[-1] + 1, rows[0]: rows[-1] + 1]
else:
image = image[:1, :1]
return image
def skeleton(img):
size = np.size(img)
skel = np.zeros(img.shape,np.uint8)
element = cv2.getStructuringElement(cv2.MORPH_CROSS,(3,3))
done = False
while( not done):
eroded = cv2.erode(img,element)
temp = cv2.dilate(eroded,element)
temp = cv2.subtract(img,temp)
skel = cv2.bitwise_or(skel,temp)
img = eroded.copy()
zeros = size - cv2.countNonZero(img)
if zeros==size:
done = True
return skel
def gamma_correction(img, correction):
img = img/255.0
img = cv2.pow(img, correction)
return np.uint8(img*255)
def auto_canny(image, sigma=0.33):
# compute the median of the single channel pixel intensities
v = np.median(image)
# apply automatic Canny edge detection using the computed median
lower = int(max(0, (1.0 - sigma) * v))
upper = int(min(255, (1.0 + sigma) * v))
edged = cv2.Canny(image, lower, upper)
# return the edged image
return edged
for file in os.listdir(path):
if file.endswith(".png"):
current = os.path.join(path, file)
img = cv2.imread(current, 0)
print 'processing ' + current
img = autocrop(img, 0)
cv2.imwrite(current + '-0-cropped.jpg', img)
height, width = img.shape[:2]
img = cv2.resize(img, (width, width))
cv2.imwrite(current + '-0-resized.jpg', img)
# cv2.imwrite(current +'-2-auto_canny_default.jpg', auto_canny(img))
# img = cv2.medianBlur(img,5)
# cv2.imwrite(current +'-0-medianBlur.jpg',img)
# th3 = cv2.adaptiveThreshold(img,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY,11,2)
# cv2.imwrite(current +'-1-threshold_gaussian.jpg',th3)
# laplacian = cv2.Laplacian(img,cv2.CV_64F)
# cv2.imwrite(current + '-3-threshold_gaussian.jpg', laplacian)
#img = cv2.bilateralFilter(img, 3, 3, 5)
edges = cv2.Canny(img,10,20,apertureSize = 5)
cv2.imwrite(current +'-1-edges-10-60.jpg',edges)
kernel = np.ones((3,3),np.uint8)
edges = cv2.morphologyEx(edges, cv2.MORPH_CLOSE, kernel)
cv2.imwrite(current +'-1-edgesClosed-10-60.jpg', edges)
edges = 255-edges
cv2.imwrite(current +'-2-edgesClosedInverted-10-60.jpg', edges)
im2, contours, hierarchy = cv2.findContours(edges, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
imgColor = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
maxArea = 0
for cnt in contours:
if maxArea < cv2.contourArea(cnt):
maxArea = cv2.contourArea(cnt)
for cnt in contours:
rect = cv2.minAreaRect(cnt) #I have used min Area rect for better result
width = rect[1][0]
height = rect[1][1]
if cv2.contourArea(cnt) > int(maxArea/2.5) and ( width < height/2 or height < width/2):
cv2.drawContours(imgColor, cnt, -1, (0,255,0), 1)
cv2.imwrite(current+'-5-Contours.jpg',imgColor)
# edges = skeleton(255-edges)
# cv2.imwrite(current +'-2-skeleton.jpg', edges)
# edges = 255-edges
# minLineLength=int(width/4)
# threshold = 20
# maxLineGap = 1
# rho = 1
# lines = cv2.HoughLinesP(image=edges,rho=rho,theta=np.pi/180, threshold=threshold,lines=np.array([]), minLineLength=minLineLength,maxLineGap=maxLineGap)
# if lines is not None:
# a,b,c = lines.shape
# for i in range(a):
# cv2.line(img, (lines[i][0][0], lines[i][0][1]), (lines[i][0][2], lines[i][0][3]), (0, 0, 255), 1, cv2.LINE_AA)
# cv2.line(edges, (lines[i][0][0], lines[i][0][1]), (lines[i][0][2], lines[i][0][3]), (0, 0, 255), 1, cv2.LINE_AA)
# cv2.imwrite(current+'-5-houghlines.jpg',img)
# cv2.imwrite(current+'-6-houghlines.jpg',edges)
# print 'cool'
# else:
# cv2.imwrite(current+'-5-houghlines.jpg',img)
Also, do check following links:
Detection of Continuous, Smooth and Thin Edges in Noisy Images Using Constrained Particle Swarm Optimisation
http://www.imagemagick.org/discourse-server/viewtopic.php?t=14491
http://answers.opencv.org/question/3454/detecting-thick-edges/