I have a binary mask, how to apply a Gaussian kernel of standard unit deviation on the border of the mask to smooth border?
When applying Gaussian blur filter on a mask, it blurs only the borders of the mask.
Example:
import cv2
orig_img = cv2.imread('mask.png', cv2.IMREAD_GRAYSCALE) # Read image as Grayscale.
blur = cv2.GaussianBlur(orig_img, (15, 15), 0)
Result:
In case you want to keep the mask unmodified, and smooth only the pixels around the mask, I suggest using few iterations, and taking the maximum.
Getting the maximum between the original image and blurred image, makes sure that the original mask pixels remains unchanged, because their values is 255 (maximum possible value).
Here is a code sample:
import cv2
orig_img = cv2.imread('mask.png', cv2.IMREAD_GRAYSCALE) # Read image as Grayscale.
img = orig_img.copy()
for i in range(10):
blur = cv2.GaussianBlur(img, (15, 15), 0)
img = cv2.max(blur, img) # Getting the maximum in order to mask the margins brighter
blur = cv2.max(orig_img, img) # Getting the maximum for keeping the original mask pixels unmodified.
cv2.imshow('blur', blur)
cv2.waitKey()
cv2.destroyAllWindows()
Result:
Another option is using morphological dilation before GaussianBlur:
import cv2
orig_img = cv2.imread('mask.png', cv2.IMREAD_GRAYSCALE) # Read image as Grayscale.
img = cv2.dilate(orig_img, cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (7, 7)))
blur = cv2.GaussianBlur(img, (15, 15), 0)
blur = cv2.max(blur, orig_img) # Getting the maximum for keeping the original mask pixels unmodified.
cv2.imshow('blur', blur)
cv2.waitKey()
cv2.destroyAllWindows()
Result:
I want to detect a specific shape which is combination of 2 shapes Pentagon and a square. However side of a square should be around 3 times of a pentagon to match a valid shape as shown in the image.
I'm learning different image processing techniques for my requirement.
Contour Detection: Issue is knowing there are 7 corners is not enough as x : 3x need to be validated.
Haar features: Issue is images consist of background and there are text inside these object. So haar will not optimal method in my opinion.
My idea
I think may be I can detect lines corners and using side lengths I can do some math and identify the image.Is there any image processing technique that use mathematical distance, scale, location to identify object?
Original image
matching
not matching
Here's a simple approach:
Obtain binary image. Load image, convert to grayscale, Gaussian blur, then Otsu's threshold.
Filter for desired contour. We find contours then filter using a combination of contour approximation + contour area. With the observation that the shapes have a large area difference, we can use a predetermined threshold area to identify between the two.
Input -> Binary image -> Detected shape
Result
Match
Input -> Binary image -> Detected shape
Result
No Match
Since you didn't specify a language, I implemented in Python
import cv2
import numpy as np
# Load image, grayscale, Gaussian blur, Otsus threshold
image = cv2.imread('1.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Find contours
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.04 * peri, True)
area = cv2.contourArea(c)
# Filter using contour approximation and area filtering (Remove small noise)
if len(approx) > 4 and len(approx) < 8 and area > 200:
# This is the larger version
if area >= 5500:
print('Match')
# Smaller version
elif area < 5500:
print('No Match')
cv2.drawContours(image, [c], -1, (255,0,12), 3)
cv2.imshow('thresh', thresh)
cv2.imshow('image', image)
cv2.waitKey()
I have this fancy image of "Brainbow image showing map of neuronal circuits of the mouse cerebral cortex"
and I want to count the number of green flashes so ran k-means on it with 15 clusters and I isolated the two colors that together do the job, but i am left with many green streaks/ tails and edges of yellow flashes.
I was hoping to find some algo that thresholds by area and select only the actual green flashes or maybe another aproach where I would not face this problem. I have used python k-means from sklearn.cluster
You could use color thresholding to isolate the green flashes. The idea is to convert the image to HSV format and define a lower/upper color threshold range. This will give you a binary mask. From here we can do additional processing by performing morphological opening with an elliptical shaped kernel to remove noise and tails. Finally we can find contours and filter using contour area with a defined threshold area to only keep the larger blobs. Here's the result:
Count: 116
Code
import numpy as np
import cv2
# Color threshold
image = cv2.imread('1.jpg')
original = image.copy()
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
lower = np.array([42, 67, 0])
upper = np.array([69, 255, 255])
mask = cv2.inRange(hsv, lower, upper)
# Perform morphological operations
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3,3))
opening = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel, iterations=1)
# Find contours and filter using contour area
cnts = cv2.findContours(opening, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
count = 0
for c in cnts:
area = cv2.contourArea(c)
if area < 5:
cv2.drawContours(opening,[c], -1, (0,0,0), -1)
else:
count += 1
result = cv2.bitwise_and(original,original,mask=opening)
print('Count: {}'.format(count))
cv2.imshow('mask', mask)
cv2.imshow('opening', opening)
cv2.imshow('result', result)
cv2.waitKey()
I want my code to find the corners of a square lego plate in an image like the one attached.
I also want to find its dimensions, i.e. the number of "blops" in both dimensions (48x48 in the attached image).
I am currently looking at detecting the individual "blops", and the result so far is pretty good: a combination of blur, adaptiveThreshold, findContours and selection based on area finds the contours rendered in the second attached image (coloring is random).
I'm now looking for an algorithm to find the "grid" losely represented by these contours (or their mid-points), but I lack the google fu. Any ideas?
(Suggestions for different approaches are also very welcome.)
(The sample image shows bricks placed in the corners - an algorithm could expect this, if it helps.)
(The sample image has a rather wild background. I'd prefer to cope with that, if possible.)
Update 8 July 2016: I'm trying to write an algorithm that looks for streaks of adjacent contours forming lines. The algo should be able to find a number of these and, from that, deduce the form of the whole plate, even with perspective. Will update if it works...
Update December 2017: The above algorithm sort of worked, although it was a bit too unpredictable. Also I got problems with perspective (adding a "thick" lego brick changes the surface) and color recognition (shadows, camera peculiarities etc). This endeavor is on hold for now. If I resume it I will try with fixed camera positions immediately above the plate and consistent lights.
Here's a potential approach using color thresholding. The idea is to convert the image to HSV format then color threshold using a lower and upper bound with the assumption that the baseplate is in gray. This will give us a mask image. From here we morph open to remove noise, find contours, and sort for the largest contour. Next we obtain the rotated bounding box coordinates and draw this onto a new blank mask. Finally we bitwise-and the mask with the input image to get our result. To find the corner coordinates, we can use cv2.goodFeaturesToTrack() to find the points on the mask. Take a look at how to find accurate corner positions of a distorted rectangle from blurry image in python? and Shi-Tomasi Corner Detector & Good Features to Track for more details
Here's a visualization of each step:
We load the image, convert to HSV format, define a lower/upper bound, and perform color thresholding using cv2.inRange()
import cv2
import numpy as np
# Load image, convert to HSV, and color threshold
image = cv2.imread('1.png')
blank_mask = np.zeros(image.shape, dtype=np.uint8)
original = image.copy()
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
lower = np.array([0, 0, 109])
upper = np.array([179, 36, 255])
mask = cv2.inRange(hsv, lower, upper)
Next we create a rectangular kernel using cv2.getStructuringElement() and perform morphological operations using cv2.morphologyEx(). This step removes small particles of noise.
# Morph open to remove noise
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
opening = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel, iterations=1)
From here we find contours on the mask using cv2.findContours() and filter using contour area to obtain the largest contour. We then obtain the rotated boding box coordinates using cv2.minAreaRect() and cv2.boxPoints() then draw this onto a new blank mask with cv2.fillPoly(). This step gives us a "perfect" outer contour of the baseplate. Here's the detected outer contour highlighted in green and the resulting mask.
# Find contours and sort for largest contour
cnts = cv2.findContours(opening, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)[0]
# Obtain rotated bounding box and draw onto a blank mask
rect = cv2.minAreaRect(cnts)
box = cv2.boxPoints(rect)
box = np.int0(box)
cv2.drawContours(image,[box],0,(36,255,12),3)
cv2.fillPoly(blank_mask, [box], (255,255,255))
Finally we bitwise-and the mask with our original input image to obtain our result. Depending on what you need, you can change the background to black or white.
# Bitwise-and mask with input image
blank_mask = cv2.cvtColor(blank_mask, cv2.COLOR_BGR2GRAY)
result = cv2.bitwise_and(original, original, mask=blank_mask)
# result[blank_mask==0] = (255,255,255) # Color background white
To detect the corner coordinates, we can use cv2.goodFeaturesToTrack(). Here's the detected corners highlighted in purple:
Coordinates:
(91.0, 525.0)
(463.0, 497.0)
(64.0, 152.0)
(436.0, 125.0)
# Detect corners
corners = cv2.goodFeaturesToTrack(blank_mask, maxCorners=4, qualityLevel=0.5, minDistance=150)
for corner in corners:
x,y = corner.ravel()
cv2.circle(image,(x,y),8,(155,20,255),-1)
print("({}, {})".format(x,y))
Full Code
import cv2
import numpy as np
# Load image, convert to HSV, and color threshold
image = cv2.imread('1.png')
blank_mask = np.zeros(image.shape, dtype=np.uint8)
original = image.copy()
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
lower = np.array([0, 0, 109])
upper = np.array([179, 36, 255])
mask = cv2.inRange(hsv, lower, upper)
# Morph open to remove noise
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
opening = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel, iterations=1)
# Find contours and sort for largest contour
cnts = cv2.findContours(opening, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)[0]
# Obtain rotated bounding box and draw onto a blank mask
rect = cv2.minAreaRect(cnts)
box = cv2.boxPoints(rect)
box = np.int0(box)
cv2.drawContours(image,[box],0,(36,255,12),3)
cv2.fillPoly(blank_mask, [box], (255,255,255))
# Bitwise-and mask with input image
blank_mask = cv2.cvtColor(blank_mask, cv2.COLOR_BGR2GRAY)
result = cv2.bitwise_and(original, original, mask=blank_mask)
result[blank_mask==0] = (255,255,255) # Color background white
# Detect corners
corners = cv2.goodFeaturesToTrack(blank_mask, maxCorners=4, qualityLevel=0.5, minDistance=150)
for corner in corners:
x,y = corner.ravel()
cv2.circle(image,(x,y),8,(155,20,255),-1)
print("({}, {})".format(x,y))
cv2.imwrite('mask.png', mask)
cv2.imwrite('opening.png', opening)
cv2.imwrite('blank_mask.png', blank_mask)
cv2.imwrite('image.png', image)
cv2.imwrite('result.png', result)
cv2.waitKey()
I am trying to find horizontal and vertical lines from an image which came from a "document". The documents are scanned pages from contracts and so the lines look like what you would see in a table or in a contract block.
I have been trying OpenCV for the job. The Hough transform implementation in OpenCV seemed useful for the job, but I could not find any combination of parameters that would allow it to cleanly find the vertical and horizontal lines. I tried with and without edge detection. No luck. If anyone has done anything similar I'm interested in knowing how.
See here an image of my before and after experimentation with HoughP in OpenCV. It's the best I could do, http://dl.dropbox.com/u/3787481/Untitled%201.png
So now I'm wondering whether there is another kind of transform I could use which would allow me to reliably find horizontal and vertical lines (and preferably dashed lines too).
I know this problem is solvable because I have Nuance and ABBYY OCR tools which can both reliably extract horizontal and vertical lines and return me the bounding box of the lines.
Thanks!
Patrick.
Have you seen a code sample from HoughLinesP function documentation?
I think you can use it as starting point for your algorithm. To pick horizontal an vertical lines you just need to filter out other lines by line angle.
UPDATE:
As I see you need to find not the lines but horizontal an vertical edges on the page. For this task you need to combine several processing steps to get good results.
For your image I'm able to get good results by combining Canny edge detection with HoughLinesP. Here is my code (I've used python, but I think you see the idea):
img = cv2.imread("C:/temp/1.png")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray, 80, 120)
lines = cv2.HoughLinesP(edges, 1, math.pi/2, 2, None, 30, 1);
for line in lines[0]:
pt1 = (line[0],line[1])
pt2 = (line[2],line[3])
cv2.line(img, pt1, pt2, (0,0,255), 3)
cv2.imwrite("C:/temp/2.png", img)
Result looks like:
Here's a complete OpenCV solution using morphological operations.
Obtain binary image
Create horizontal kernel and detect horizontal lines
Create vertical kernel and detect vertical lines
Here's a visualization of the process. Using this input image:
Binary image
import cv2
# Load image, convert to grayscale, Otsu's threshold
image = cv2.imread('1.png')
result = image.copy()
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
Detected horizontal lines highlighted in green
# Detect horizontal lines
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (40,1))
detect_horizontal = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)
cnts = cv2.findContours(detect_horizontal, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(result, [c], -1, (36,255,12), 2)
Detected vertical lines highlighted in green
# Detect vertical lines
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,10))
detect_vertical = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, vertical_kernel, iterations=2)
cnts = cv2.findContours(detect_vertical, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(result, [c], -1, (36,255,12), 2)
Result
Here's the output using another input image
Input -> Binary -> Detected Horizontal -> Detected Vertical -> Result
Note: Depending on the image, you may have to modify the kernel size. For instance to capture longer horizontal lines, it may be necessary to increase the horizontal kernel from (40, 1) to say (80, 1). If you wanted to detect thicker horizontal lines, then you could increase the width of the kernel to say (80, 2). In addition, you could increase the number of iterations when performing cv2.morphologyEx(). Similarly, you could modify the vertical kernels to detect more or less vertical lines. There is a trade-off when increasing or decreasing the kernel size as you may capture more or less of the lines. Again, it all varies depending on the input image
Full code for completeness
import cv2
# Load image, convert to grayscale, Otsu's threshold
image = cv2.imread('1.png')
result = image.copy()
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Detect horizontal lines
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (40,1))
detect_horizontal = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)
cnts = cv2.findContours(detect_horizontal, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(result, [c], -1, (36,255,12), 2)
# Detect vertical lines
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,10))
detect_vertical = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, vertical_kernel, iterations=2)
cnts = cv2.findContours(detect_vertical, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(result, [c], -1, (36,255,12), 2)
cv2.imshow('result', result)
cv2.waitKey()
If you just want the "lines" and not the "line segments", I would avoid using Canny, Hough, FindContours or any other such function in case you want more speed in your code. If your images are not rotated and what you want to find is always vertical or horizontal, I would just use cv::Sobel (one for vertical, and another for horizontal) and create accumulation arrays for columns and rows. Then you can search for maxima in such accumulations or profiles, for instance by setting a threshold, and you will know the row or column in which there is a vertical or horizontal edge lines.
You might consider leaving the Hough line detection since this method looks for "global" lines, not necessarily line segments. I recently implemented an application that identified "parallelograms" - essentially squares that might be rotated and perspective fore-shortened due to viewing angle. You might consider something similar. My pipeline was:
Convert from RGB to grayscale (cvCvtColor)
Smooth (cvSmooth)
Threshold (cvThreshold)
Detect edges (cvCanny)
Find contours (cvFindContours)
Approximate contours with linear features (cvApproxPoly)
In your application, the resulting contour list will likely be large (depending upon the "aggressiveness" of smoothing and the feature enhancement of the Canny edge detector. You can prune this list by a variety of parameters: number of points returned from the contour finder, area of the contour (cvContourArea), etc. From my experience, I would expect that "valid" lines in your application would have well-defined area and vertex count properties. Additionally, you can filter out contours based on distance between end-points, angle defined by the line connecting end-points, etc.
Depending upon how much CPU "time" you have, you can always pair the Hough algorithm with an algorithm like that above to robustly identify horizontal and vertical lines.
Don´t convert the RGB to grayscale. Sometimes, different colors in RGB can be merged to the same grayscale value, so it could miss some contours. You should analyze each of the RGB channels separately.
Here is an approach that accumulates arrays for columns and rows. Then one can search for maxima in such accumulations (above a certain threshold) and deduce in which row or column there is a vertical or horizontal line.
If you want to quickly test the code, use the following Google Colab Notebook.
Google Colab Notebook
import numpy as np
import cv2
import scipy
from scipy.signal import find_peaks
from matplotlib import pyplot as plt
url = "https://i.stack.imgur.com/S00ap.png"
!wget $url -q -O input.jpg
fileName = 'input.jpg'
img = cv2.imread(fileName)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
tmp = img.copy()
gray = cv2.cvtColor(tmp, cv2.COLOR_BGR2GRAY)
blurred = cv2.bilateralFilter(gray, 11, 61, 39)
edges = cv2.Canny(blurred, 0, 255)
v_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,3))
h_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (7,1))
v_morphed = cv2.morphologyEx(edges, cv2.MORPH_OPEN, v_kernel, iterations=2)
v_morphed = cv2.dilate(v_morphed, None)
h_morphed = cv2.morphologyEx(edges, cv2.MORPH_OPEN, h_kernel, iterations=2)
h_morphed = cv2.dilate(h_morphed, None)
v_acc = cv2.reduce(v_morphed, 0, cv2.REDUCE_SUM, dtype=cv2.CV_32S)
h_acc = cv2.reduce(h_morphed, 1, cv2.REDUCE_SUM, dtype=cv2.CV_32S)
def smooth(y, box_pts):
box = np.ones(box_pts)/box_pts
y_smooth = np.convolve(y, box, mode='same')
return y_smooth
s_v_acc = smooth(v_acc[0,:],9)
s_h_acc = smooth(h_acc[:,0],9)
v_peaks, v_props = find_peaks(s_v_acc, 0.70*np.max(np.max(s_v_acc)))
h_peaks, h_props = find_peaks(s_h_acc, 0.70*np.max(np.max(s_h_acc)))
for peak_index in v_peaks:
cv2.line(tmp, (peak_index, 0), (peak_index, img.shape[0]), (255, 0, 0),2)
for peak_index in h_peaks:
cv2.line(tmp, (0, peak_index), (img.shape[1], peak_index), (0, 0, 255),2)
v_height = v_props['peak_heights'] #list of the heights of the peaks
h_height = h_props['peak_heights'] #list of the heights of the peaks
def align_axis_x(ax, ax_target):
"""Make x-axis of `ax` aligned with `ax_target` in figure"""
posn_old, posn_target = ax.get_position(), ax_target.get_position()
ax.set_position([posn_target.x0, posn_old.y0, posn_target.width, posn_old.height])
def align_axis_y(ax, ax_target):
"""Make y-axis of `ax` aligned with `ax_target` in figure"""
posn_old, posn_target = ax.get_position(), ax_target.get_position()
ax.set_position([posn_old.x0, posn_target.y0, posn_old.width, posn_target.height])
fig = plt.figure(constrained_layout=False, figsize=(24,16))
spec = fig.add_gridspec(ncols=4, nrows=2, height_ratios=[1, 1])
ax1 = fig.add_subplot(spec[0,0])
ax1.imshow(tmp)
ax2 = fig.add_subplot(spec[0, 1])
ax2.imshow(v_morphed)
ax3 = fig.add_subplot(spec[0, 2])
ax3.imshow(h_morphed)
ax4 = fig.add_subplot(spec[0, 3], sharey=ax3)
ax4.plot(h_acc[:,0], np.arange(len(h_acc[:,0])), 'y', marker="o", ms=1, mfc="k", mec="k")
ax4.plot(s_h_acc, np.arange(len(s_h_acc)), 'r', lw=1)
ax4.plot(h_height, h_peaks, "x", lw="5")
ax5 = fig.add_subplot(spec[1, 1], sharex=ax2)
ax5.plot(np.arange(len(v_acc[0,:])), v_acc[0,:], 'y', marker="o", ms=1, mfc="k", mec="k")
ax5.plot(np.arange(len(s_v_acc)), s_v_acc, 'r', lw=2)
ax5.plot(v_peaks, v_height, "x", lw="5")
plt.tight_layout()
align_axis_y(ax4,ax3)
align_axis_x(ax5,ax2)