Develop Reference

Masked out large irregular shape from image with Python

The objective is to remove large irregular area and maintained only character in the image.
For example, given the following
and the expected masked output
I have the impression this can be achieved as below
import cv2
import numpy as np
from matplotlib import pyplot as plt
dpath='remove_bg1.jpg'
img = cv2.imread(dpath)
img_fh=img.copy()
cv2.bitwise_not(img_fh,img_fh)
ksize=10
kernel = np.ones((ksize,ksize),np.uint8)
erosion = cv2.erode(img_fh,kernel,iterations = 3)
invertx = cv2.bitwise_not(erosion)
masked = cv2.bitwise_not(cv2.bitwise_and(img_fh,invertx))
all_image=[img,invertx,masked]
ncol=len(all_image)
for idx, i in enumerate(all_image):
plt.subplot(int(f'1{ncol}{idx+1}')),plt.imshow(i)
plt.show()
which produce
Clearly, the code above did not produced the expected result.
May I know how to address this issue properly?

To remove the unwanted blob, we must create a mask such that it encloses it completely.
Flow:
Inversely binarize the image (such that you have a white foreground against dark background)
Dilate the image (since the blob makes contact with letter 'A', it has to be isolated )
Find contour with the largest area
Draw the contour on an another 1-channel image and thicken it (dilation)
Pixel Assignment: Pixels containing the dilated blob are made white on the original image
Code:
im = cv2.imread('stained_text.jpg')
im2 = im.copy()
gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
# inverse binaraization
th = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
Notice the blob region touching the letter 'A'. Hence to isolate it we perform erosion using an elliptical kernel
# erosion
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5,5))
erode = cv2.erode(th, kernel, iterations=2)
# find contours
contours, hierarchy = cv2.findContours(erode, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
# Contour of maximum area
c = max(contours, key = cv2.contourArea)
# create 1-channel image in black
black = np.zeros((im.shape[0], im.shape[1]), np.uint8)
# draw the contour on it
black = cv2.drawContours(black, [c], 0, 255, -1)
# perform dilation to have clean border
# we are using the same kernel
dilate = cv2.dilate(black, kernel, iterations = 3)
# assign the dilated area in white over the original image
im2[dilate == 255] = (255,255,255)
This was just one of the many possible ways on how to proceed. The key thing to note is how to isolate the blob.

Get the location of all contours present in image using opencv, but skipping text

I want to retrieve all contours of the image below, but ignore text.
Image:
When I try to find the contours of the current image I get the following:
I have no idea how to go about this as I am new to using OpenCV and image processing. I want to get ignore the text, how can I achieve this? If ignoring is not possible but making a single bounding box surrounding the text is, than that would be good too.
Edit:
Criteria that I need to match:
The contours may very in size and shape.
The colors from the image may differ.
The colors and size of the text inside the image may differ.

Here is one way to do that in Python/OpenCV.
Read the input
Convert to grayscale
Get Canny edges
Apply morphology close to ensure they are closed
Get all contour hierarchy
Filter contours to keep only those above threshold in perimeter
Draw contours on input
Draw each contour on a black background
Save results
Input:
import numpy as np
import cv2
# read input
img = cv2.imread('short_title.png')
# convert to gray
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# get canny edges
edges = cv2.Canny(gray, 1, 50)
# apply morphology close to ensure they are closed
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3,3))
edges = cv2.morphologyEx(edges, cv2.MORPH_CLOSE, kernel)
# get contours
contours = cv2.findContours(edges, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
contours = contours[0] if len(contours) == 2 else contours[1]
# filter contours to keep only large ones
result = img.copy()
i = 1
for c in contours:
perimeter = cv2.arcLength(c, True)
if perimeter > 500:
cv2.drawContours(result, c, -1, (0,0,255), 1)
contour_img = np.zeros_like(img, dtype=np.uint8)
cv2.drawContours(contour_img, c, -1, (0,0,255), 1)
cv2.imwrite("short_title_contour_{0}.jpg".format(i),contour_img)
i = i + 1
# save results
cv2.imwrite("short_title_gray.jpg", gray)
cv2.imwrite("short_title_edges.jpg", edges)
cv2.imwrite("short_title_contours.jpg", result)
# show images
cv2.imshow("gray", gray)
cv2.imshow("edges", edges)
cv2.imshow("result", result)
cv2.waitKey(0)
Grayscale:
Edges:
All contours on input:
Contour 1:
Contour 2:
Contour 3:
Contour 4:

Here are two options for erasing the text:
Using pytesseract OCR.
Finding white (and small) connected components.
Both solution build a mask, dilate the mask and use cv2.inpaint for erasing the text.
Using pytesseract:
Find text boxes using pytesseract.image_to_boxes.
Fill the boxes in the mask with 255.
Code sample:
import cv2
import numpy as np
from pytesseract import pytesseract, Output
# Tesseract path
pytesseract.tesseract_cmd = "C:\\Program Files\\Tesseract-OCR\\tesseract.exe"
img = cv2.imread('ShortAndInteresting.png')
# https://stackoverflow.com/questions/20831612/getting-the-bounding-box-of-the-recognized-words-using-python-tesseract
boxes = pytesseract.image_to_boxes(img, lang='eng', config=' --psm 6') # Run tesseract, returning the bounding boxes
h, w, _ = img.shape # assumes color image
mask = np.zeros((h, w), np.uint8)
# Fill the bounding boxes on the image
for b in boxes.splitlines():
b = b.split(' ')
mask = cv2.rectangle(mask, (int(b[1]), h - int(b[2])), (int(b[3]), h - int(b[4])), 255, -1)
mask = cv2.dilate(mask, np.ones((5, 5), np.uint8)) # Dilate the boxes in the mask
clean_img = cv2.inpaint(img, mask, 2, cv2.INPAINT_NS) # Remove the text using inpaint (replace the masked pixels with the neighbor pixels).
# Show mask and clean_img for testing
cv2.imshow('mask', mask)
cv2.imshow('clean_img', clean_img)
cv2.waitKey()
cv2.destroyAllWindows()
Mask:
Finding white (and small) connected components:
Use mask = cv2.inRange(img, (230, 230, 230), (255, 255, 255)) for finding the text (assume the text is white).
Finding connected components in the mask using cv2.connectedComponentsWithStats(mask, 4)
Remove large components from the mask - fill components with large area with zeros.
Code sample:
import cv2
import numpy as np
img = cv2.imread('ShortAndInteresting.png')
mask = cv2.inRange(img, (230, 230, 230), (255, 255, 255))
nlabel, labels, stats, centroids = cv2.connectedComponentsWithStats(mask, 4) # Finding connected components with statistics
# Remove large components from the mask (fill components with large area with zeros).
for i in range(1, nlabel):
area = stats[i, cv2.CC_STAT_AREA] # Get area
if area > 1000:
mask[labels == i] = 0 # Remove large connected components from the mask (fill with zero)
mask = cv2.dilate(mask, np.ones((5, 5), np.uint8)) # Dilate the text in the maks
cv2.imwrite('mask2.png', mask)
clean_img = cv2.inpaint(img, mask, 2, cv2.INPAINT_NS) # Remove the text using inpaint (replace the masked pixels with the neighbor pixels).
# Show mask and clean_img for testing
cv2.imshow('mask', mask)
cv2.imshow('clean_img', clean_img)
cv2.waitKey()
cv2.destroyAllWindows()
Mask:
Clean image:
Note:
My assumption is that you know how to split the image into contours, and the only issue is the present of the text.

I would recommend using flood fill, find the seed point for each color region, flood fill it to ignore the text values within. Hope that helps!
Refer to example of using floodfill here: https://www.programcreek.com/python/example/89425/cv2.floodFill
Example below copied from link above
def fillhole(input_image):
'''
input gray binary image get the filled image by floodfill method
Note: only holes surrounded in the connected regions will be filled.
:param input_image:
:return:
'''
im_flood_fill = input_image.copy()
h, w = input_image.shape[:2]
mask = np.zeros((h + 2, w + 2), np.uint8)
im_flood_fill = im_flood_fill.astype("uint8")
cv.floodFill(im_flood_fill, mask, (0, 0), 255)
im_flood_fill_inv = cv.bitwise_not(im_flood_fill)
img_out = input_image | im_flood_fill_inv
return img_out

Delete unused shapes in OpenCV

I've got a shape detection with OpenCV in Python going on; bolts and nuts. I take a picture, make it binary, and detect edges. Now the white area is always grainy because of dust and grime. My detection uses the largest areas as parts, which works great. But how can I delete the thousands of objects caused by dust? 
In short, I want to reduce the array of shapes to only the biggest ones for further processing.

Here is one way to do that as per my comment above using Python/OpenCV.
From your binary image get the contours. Then select the largest contour. Then draw a white filled contour on a black background image the same size as your input as a mask. Then use numpy to blacken everything in your image that is black in your mask.
Input:
import cv2
import numpy as np
# load image
img = cv2.imread("coke_bottle2.png")
hh, ww = img.shape[:2]
# convert to gray
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# threshold using inRange
thresh = cv2.threshold(gray, 50, 255, cv2.THRESH_BINARY)[1]
# apply morphology closing to fill black holes and smooth outline
# could use opening to remove white spots, but we will use contours
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (25,25))
thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
# get the largest contour
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)
# draw largest contour as white filled on black background as mask
mask = np.zeros((hh,ww), dtype=np.uint8)
cv2.drawContours(mask, [big_contour], 0, 255, -1)
# use mask to black all but largest contour
result = img.copy()
result[mask==0] = (0,0,0)
# write result to disk
cv2.imwrite("coke_bottle2_threshold.png", thresh)
cv2.imwrite("coke_bottle2_mask.png", mask)
cv2.imwrite("coke_bottle2_background_removed.jpg", result)
# display it
cv2.imshow("thresh", thresh)
cv2.imshow("mask", mask)
cv2.imshow("result", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Threshold Image (contains small extraneous white regions):
Mask Image (only the largest filled contour):
Result:

How to crop circle image from webcam OpenCV and remove background

I am applying filter. By using OpenCv live webcam is open and it detect face and apply filter. But i want to crop the face in circle and removed the extra background and save the image.
for example:
to this
How can i implement in python?

The idea is to create a black mask then draw the desired region to crop out in white using cv2.circle(). From there we can use cv2.bitwise_and() with the original image and the mask. To crop the result, we can use cv2.boundingRect() on the mask to obtain the ROI then use Numpy slicing to extract the result. For this example I used the center point as (335, 245). You can adjust the circle radius to increase or decrease the size of the circle.
Code
import cv2
import numpy as np
# Create mask and draw circle onto mask
image = cv2.imread('1.jpg')
mask = np.zeros(image.shape, dtype=np.uint8)
x,y = 335, 245
cv2.circle(mask, (x,y), 110, (255,255,255), -1)
# Bitwise-and for ROI
ROI = cv2.bitwise_and(image, mask)
# Crop mask and turn background white
mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
x,y,w,h = cv2.boundingRect(mask)
result = ROI[y:y+h,x:x+w]
mask = mask[y:y+h,x:x+w]
result[mask==0] = (255,255,255)
cv2.imshow('result', result)
cv2.waitKey()

How to detect multiple colored regions in an image and produce individual crops for each with Python OpenCV?

I have an image like this:
And I want to crop the image anywhere there is red.
So with this image I would be looking to produce 4 crops:
Obviously I first need to detect anywhere there is red in the image. I can do the following:
import cv2
import numpy as np
from google.colab.patches import cv2_imshow
## (1) Read and convert to HSV
img = cv2.imread("my_image_with_red.png")
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
## (2) Find the target red region in HSV
hsv_lower = np.array([0,50,50])
hsv_upper = np.array([10,255,255])
mask = cv2.inRange(hsv, hsv_lower, hsv_upper)
## (3) morph-op to remove horizone lines
kernel = np.ones((5,1), np.uint8)
mask2 = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel)
## (4) crop the region
ys, xs = np.nonzero(mask2)
ymin, ymax = ys.min(), ys.max()
xmin, xmax = xs.min(), xs.max()
croped = img[ymin:ymax, xmin:xmax]
pts = np.int32([[xmin, ymin],[xmin,ymax],[xmax,ymax],[xmax,ymin]])
cv2.drawContours(img, [pts], -1, (0,255,0), 1, cv2.LINE_AA)
cv2_imshow(croped)
cv2_imshow(img)
cv2.waitKey()
Which gives the following result:
The bounding box covers the entire area containing red.
How can I get bounding boxes around each red piece of the image? I have looked into multiple masks but this doesn't seem to work.
What I am looking for is:
detect each red spot in the image;
return boundaries on each red dot;
use those boundaries to produce 4 individual crops as new images.

There are currently several problems:
If you look at your mask image, you will see that all traces of red are captured on the mask including the small noise. You're currently using np.nonzero() which captures all white pixels. This is what causes the bounding box to cover the entire area. To fix this, we can tighten up the lower hsv threshold to get this resulting mask:
Note there are still a lot of small blobs. Your question should be rephrased to
How can I crop the large red regions?
If you want to capture all red regions, you will obtain much more then 4 crops. So to remedy this, we will perform morphological operations to remove the small noise and keep only the large pronounced red regions. This results in a mask image that contains the large regions
You do not require multiple masks
How can I get bounding boxes around each red piece of the image?
You can do this using cv2.findContours() on the mask image to return the bounding rectangles of each red dot.
Oh? This is not your desired result. Since your desired result has some space surrounding each red dot, we also need to include a offset to the bounding rectangle. After adding an offset, here's our result
Since we have the bounding rectangles, we can simply use Numpy slicing to extract and save each ROI. Here's the saved ROIs
So to recap, to detect each red spot in the image, we can use HSV color thresholding. Note this will return all pixels which match this threshold which may be different from what you expect so it is necessary to perform morphological operations to filter the resulting mask. To obtain the bounding rectangles on each red blob, we can use cv2.findContours() which will give us the ROIs using cv2.boundingRect(). Once we have the ROI, we add a offset and extract the ROI using Numpy slicing.
import cv2
import numpy as np
image = cv2.imread("1.png")
original = image.copy()
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
hsv_lower = np.array([0,150,50])
hsv_upper = np.array([10,255,255])
mask = cv2.inRange(hsv, hsv_lower, hsv_upper)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
opening = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel, iterations=1)
close = cv2.morphologyEx(opening, cv2.MORPH_CLOSE, kernel, iterations=1)
cnts = cv2.findContours(close, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
offset = 20
ROI_number = 0
for c in cnts:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(image, (x - offset, y - offset), (x + w + offset, y + h + offset), (36,255,12), 2)
ROI = original[y-offset:y+h+offset, x-offset:x+w+offset]
cv2.imwrite('ROI_{}.png'.format(ROI_number), ROI)
ROI_number += 1
cv2.imshow('mask', mask)
cv2.imshow('close', close)
cv2.imshow('image', image)
cv2.waitKey()