We Keep Coding

How to plot the shortest distance between two lines passing through an arbitrary point using OpenCV in Python?

I have a picture with lines drawn on it.
And, I want to draw a straight line with the shortest distance between two lines passing through an arbitrary point.
with Python OpenCV
This is a code that can extract green from the original image and draw dots with mouse from the thinned image.
import numpy as np
import cv2
def on_mouse(event, x,y,flags,param):
if event == cv2.EVENT_LBUTTONDOWN:
cv2.line(img,(x,y),(x,y),(255,0,0),2)
cv2.imshow('thinned',thinned)
def colorPickandThinning(img):
height, width = img.shape[:2]
img_hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
lower_green = (40,60,0)
upper_green = (80, 255, 255)
img_mask = cv2.inRange(img_hsv, lower_green, upper_green)
img[:, :, 0] = 0
img[:, :, 2] = 0
img[:, :, 1] = img_mask
img_temp = img
# filtering image nosiecancel
noisecancel = cv2.fastNlMeansDenoisingColored(img_temp,None,49,57,7,21)
cv2.imshow('noise',noisecancel)
#thinning
thinned = cv2.ximgproc.thinning(cv2.cvtColor(noisecancel,cv2.COLOR_RGB2GRAY))
return thinned
img = cv2.imread('test_img.jpg')
thinned = colorPickandThinning(img)
cv2.imshow('thinned',thinned)
cv2.setMouseCallback('thinned',on_mouse,thinned)
cv2.waitKey(0)
cv2.destroyAllWindows()
This is a result picture and I drew a dot with the mouse.
I want to draw like this picture.

opencv align two images by keypoints with stretching

I have two images
image1 (object):
]3
Original image without marked keypoints:
image2 is a white picture (500x500)
In image1 and in image2 I have marked keypoints.
I want to align image1 on image2 by keypoints. So the goal that both keypoints overlaps with stretching, scaling and transforming image2.
This are my keypoints (csv file). The coordinates are x and y for image1 in image1 and for image2 in image2.
object1_x,object1_y,image_x,image_y
0,0,80,137
286,0,409,42
286,198,416,390
174,198,331,384
158,116,291,119
0,97,111,311
How can I do this with opencv and python?
So the result image should looks like this (without the red dots, the red dots are only for demonstration the keypoints):

The Concept
Extract sets of 3 indices from the first set of keypoints that will form triangles when indexed from both sets of keypoints. With the indices we can get corresponding triangles from both sets of keypoints, allowing us to build the warped image triangle by triangle (see Warp one triangle to another using OpenCV for more details):
image1.png (with added points):
image2.png (with added points):
Result (with added points)
The Code
import cv2
import numpy as np
def triangles(points):
points = np.where(points, points, 1)
subdiv = cv2.Subdiv2D((*points.min(0), *points.max(0)))
subdiv.insert(list(points))
for pts in subdiv.getTriangleList().reshape(-1, 3, 2):
yield [np.where(np.all(points == pt, 1))[0][0] for pt in pts]
def crop(img, pts):
x, y, w, h = cv2.boundingRect(pts)
img_cropped = img[y: y + h, x: x + w]
pts[:, 0] -= x
pts[:, 1] -= y
return img_cropped, pts
def warp(img1, img2, pts1, pts2):
for indices in triangles(pts1):
img1_cropped, triangle1 = crop(img1, pts1[indices])
img2_cropped, triangle2 = crop(img2, pts2[indices])
transform = cv2.getAffineTransform(np.float32(triangle1), np.float32(triangle2))
img2_warped = cv2.warpAffine(img1_cropped, transform, img2_cropped.shape[:2][::-1], None, cv2.INTER_LINEAR, cv2.BORDER_REFLECT_101)
mask = np.zeros_like(img2_cropped)
cv2.fillConvexPoly(mask, np.int32(triangle2), (1, 1, 1), 16, 0)
img2_cropped *= 1 - mask
img2_cropped += img2_warped * mask
img1 = cv2.imread("image1.png")
img2 = cv2.imread("image2.png")
pts1 = np.array([[0, 0], [286, 0], [286, 198], [174, 198], [158, 116], [0, 97]])
pts2 = np.array([[80, 37], [409, 42], [416, 390], [331, 384], [291, 119], [111, 311]])
warp(img1, img2, pts1, pts2)
for pt in pts2:
cv2.circle(img2, tuple(pt), 15, (0, 0, 255), -1)
cv2.imshow("Original", img1)
cv2.imshow("Transformed", img2)
cv2.waitKey(0)
cv2.destroyAllWindows()
The Output
The Explanation
Import the necessary libraries:
import cv2
import numpy as np
Define a function, triangles, that will take in an array of coordinates, points, and yield lists of 3 indices of the array for triangles that will cover the area of the original array of coordinates:
def triangles(points):
points = np.where(points, points, 1)
subdiv = cv2.Subdiv2D((*points.min(0), *points.max(0)))
subdiv.insert(list(points))
for pts in subdiv.getTriangleList().reshape(-1, 3, 2):
yield [np.where(np.all(points == pt, 1))[0][0] for pt in pts]
Define a function, crop, that will take in an image array, img, and an array of three coordinates, pts. It will return a rectangular segment of the image just large enough to fit the triangle formed by the three point, and return the array of three coordinates transferred to the top-left corner of image:
def crop(img, pts):
x, y, w, h = cv2.boundingRect(pts)
img_cropped = img[y: y + h, x: x + w]
pts[:, 0] -= x
pts[:, 1] -= y
return img_cropped, pts
Define a function, warp, that will take in 2 image arrays, img1 and img2, and 2 arrays of coordinates, pts1 and pts2. It will utilize the triangles function defined before iterate through the triangles from the first array of coordinates, the crop function defined before to crop both images at coordinates corresponding to the triangle indices and use the cv2.warpAffine() method to warp the image at the current triangle of the iterations:
def warp(img1, img2, pts1, pts2):
for indices in triangles(pts1):
img1_cropped, triangle1 = crop(img1, pts1[indices])
img2_cropped, triangle2 = crop(img2, pts2[indices])
transform = cv2.getAffineTransform(np.float32(triangle1), np.float32(triangle2))
img2_warped = cv2.warpAffine(img1_cropped, transform, img2_cropped.shape[:2][::-1], None, cv2.INTER_LINEAR, cv2.BORDER_REFLECT_101)
mask = np.zeros_like(img2_cropped)
cv2.fillConvexPoly(mask, np.int32(triangle2), (1, 1, 1), 16, 0)
img2_cropped *= 1 - mask
img2_cropped += img2_warped * mask
Read in your images. In your case, img1 is the image we want to warp, and img2 is the blank 500 x 500 image. Also, define 2 array of coordinates to be the keypoints of the images:
img1 = cv2.imread("image1.png")
img2 = cv2.imread("image2.png")
pts1 = np.array([[0, 0], [286, 0], [286, 198], [174, 198], [158, 116], [0, 97]])
pts2 = np.array([[80, 37], [409, 42], [416, 390], [331, 384], [291, 119], [111, 311]])
Finally, use the warp function defined before to warp img1 to have its keypoints overlap with the kewpoints of img2 and show the resulting image. I drew the points from the second array of coordinates onto the resulting warped image to make the warping process easier to visualize:
warp(img1, img2, pts1, pts2)
for pt in pts2:
cv2.circle(img2, tuple(pt), 15, (0, 0, 255), -1)
cv2.imshow("Original", img1)
cv2.imshow("Transformed", img2)
cv2.waitKey(0)
cv2.destroyAllWindows()

pytesseract detects the wrong integer values

I'm trying to detects the numbers found in my sqares, and I thought I could use the libary pytesseract, but for some reason I read the wrong values.
This is the console output:
And here I have all my pictures (they are seperated, this is just to show them all)
import numpy as np
import cv2
import re
from PIL import Image
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract'
img = cv2.imread('gulRecNum.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# convert to HSV, since red and yellow are the lowest hue colors and come before green
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
# create a binary thresholded image on hue between red and yellow
lower = (0,240,160)
upper = (30,255,255)
thresh = cv2.inRange(hsv, lower, upper)
# apply morphology
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (9,9))
clean = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (15,15))
clean = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
# get external contours
contours = cv2.findContours(clean, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
result1 = img.copy()
result2 = img.copy()
mask = np.zeros(result2.shape, dtype=np.uint8)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
ROI_number = 0
for c in contours:
cv2.drawContours(result1,[c],0,(0,0,0),2)
# get rotated rectangle from contour
rot_rect = cv2.minAreaRect(c)
box = cv2.boxPoints(rot_rect)
box = np.int0(box)
# draw rotated rectangle on copy of img
cv2.drawContours(result2,[box],0,(0,0,0),2)
# Gør noget hvis arealet er større end 1.
# Whats the area of the component?
areal = cv2.contourArea(c)
if(areal > 1):
# get the center of mass
M = cv2.moments(c)
cx = int(M['m10']/M['m00'])
cy = int(M['m01']/M['m00'])
center = (cx, cy)
print("\nx: ",cx,"\ny: ",cy)
color = (0, 0, 255)
cv2.circle(result2, center, 3, color, -1)
cv2.putText(result2, "center", (int(cx) - 10, int(cy) - 20),
cv2.FONT_HERSHEY_SIMPLEX, 1.2, color, 2)
# LOOK AT THIS PART
x,y,w,h = cv2.boundingRect(c)
ROI = 255 - thresh[y:y+h, x:x+w]
cv2.drawContours(mask, [c], -1, (255,255,255), -1)
cv2.imwrite('ROI_{}.png'.format(ROI_number), ROI)
Number = pytesseract.image_to_string(ROI, config='--psm 13 --oem 3 -c tessedit_char_whitelist=0123456789')
print("Number ", Number)
ROI_number += 1
# save result
cv2.imwrite("4cubes_result2.png",result2)
# display result
imS = cv2.resize(result2, (600, 400))
cv2.imshow("result2", imS)
cv2.waitKey(0)
cv2.destroyAllWindows()
Thought I could write Number = pytesseract.image_to_string(ROI, config='--psm 13 --oem 3 -c tessedit_char_whitelist=0123456789') print(Number)
and then get the number from the image, but I don't, how can that be?
EDIT NEW ERROR
how do i solve it with this picture?
from PIL import Image
from operator import itemgetter
import numpy as np
import easyocr
import cv2
import re
import imutils
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract'
reader = easyocr.Reader(['ch_sim','en']) # need to run only once to load model into memory
#Define empty array
Cubes = []
def getNumber(ROI):
img = cv2.imread(ROI)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(gray,127,255,0)
#cv2.imshow(thresh)
#cv2.imshow('Thresholded original',thresh)
#cv2.waitKey(0)
## Get contours
contours,h = cv2.findContours(thresh,cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
## only draw contour that have big areas
imx = img.shape[0]
imy = img.shape[1]
lp_area = (imx * imy) / 10
tmp_img = img.copy()
for cnt in contours:
approx = cv2.approxPolyDP(cnt,0.01 * cv2.arcLength(cnt, True), True)
if cv2.contourArea(cnt) > lp_area:
# Draw box corners and minimum area rectangle
rect = cv2.minAreaRect(cnt)
box = cv2.boxPoints(rect)
box = np.int0(box)
#cv2.drawContours(tmp_img, [box], 0, (0, 50, 255), 3)
#cv2.circle(tmp_img, tuple(box[0]), 8, (0, 255, 0), -1)
#cv2.circle(tmp_img, tuple(box[1]), 8, (0, 255, 0), -1)
#cv2.circle(tmp_img, tuple(box[2]), 8, (0, 255, 0), -1)
#cv2.circle(tmp_img, tuple(box[3]), 8, (0, 255, 0), -1)
#cv2.imshow(tmp_img)
#cv2.imshow('Minimum Area Rectangle', tmp_img)
#cv2.waitKey(0)
## Correct orientation and crop
# Link, https://jdhao.github.io/2019/02/23/crop_rotated_rectangle_opencv/
width = int(rect[1][0])
height = int(rect[1][1])
src_pts = box.astype("float32")
dst_pts = np.array([[0, height-1],
[0, 0],
[width-1, 0],
[width-1, height-1]], dtype="float32")
M = cv2.getPerspectiveTransform(src_pts, dst_pts)
warped = cv2.warpPerspective(img, M, (width, height))
# Run OCR on cropped image
# If the predicted value is digit print else rotate first
result = reader.readtext(warped)
print(result)
predicted_digit = result[0][1]
if np.char.isdigit(predicted_digit) == True:
cv2.imshow("warped " + ROI,warped)
else:
rot_img = warped.copy()
for i in range(0, 3):
rotated_image = cv2.rotate(rot_img, cv2.cv2.ROTATE_90_CLOCKWISE)
result = reader.readtext(rotated_image)
#if np.array(result).size == 0:
# continue
if not result:
rot_img = rotated_image
continue
#if len(result) == 0:
# continue
predicted_digit = result[0][1]
#print(result)
#print(predicted_digit)
#cv2.imshow(rotated_image)
if np.char.isdigit(predicted_digit) == True:
cv2.imshow("Image " + ROI, rotated_image)
break
rot_img = rotated_image
return predicted_digit
def sortNumbers(Cubes):
Cubes = sorted(Cubes, key=lambda x: int(x[2]))
#Cubes.sort(key=itemgetter(2)) # In-place sorting
#Cubes = sorted(Cubes, key=itemgetter(2)) # Create a new list
return Cubes
#img = cv2.imread('gulRecNum.jpg')
img = cv2.imread('webcam7.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# convert to HSV, since red and yellow are the lowest hue colors and come before green
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
# create a binary thresholded image on hue between red and yellow
#Change these if cube colours changes?
lower =(20, 100, 100)
upper = (30, 255, 255)
#lower = (0,240,160)
#upper = (30,255,255)
thresh = cv2.inRange(hsv, lower, upper)
# apply morphology
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (9,9))
clean = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (15,15))
clean = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
# get external contours
contours = cv2.findContours(clean, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
result2 = img.copy()
mask = np.zeros(result2.shape, dtype=np.uint8)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
ROI_number = 0
for c in contours:
cv2.drawContours(result2,[c],0,(0,0,0),2)
# get rotated rectangle from contour
rot_rect = cv2.minAreaRect(c)
box = cv2.boxPoints(rot_rect)
box = np.int0(box)
# draw rotated rectangle on copy of img
cv2.drawContours(result2,[box],0,(0,0,0),2)
# Gør noget hvis arealet er større end 1.
# Whats the area of the component?
areal = cv2.contourArea(c)
if(areal > 1):
# get the center of mass
M = cv2.moments(c)
cx = int(M['m10']/M['m00'])
cy = int(M['m01']/M['m00'])
center = (cx, cy)
print("\nx: ",cx,"\ny: ",cy)
color = (0, 0, 255)
cv2.circle(result2, center, 3, color, -1)
cv2.putText(result2, "center", (int(cx) - 10, int(cy) - 20),
cv2.FONT_HERSHEY_SIMPLEX, 1.2, color, 2)
x,y,w,h = cv2.boundingRect(c)
ROI = 255 - thresh[y:y+h, x:x+w]
cv2.drawContours(mask, [c], -1, (255,255,255), -1)
cv2.imwrite('ROI_{}.png'.format(ROI_number), ROI)
#Read saved image (number)
result = getNumber('ROI_{}.png'.format(ROI_number))
print("ROI_number: ", result)
Cubes.append([cx, cy, result])
ROI_number += 1
# save result
cv2.imwrite("4cubes_result2.png",result2)
# display result
imS = cv2.resize(result2, (600, 400))
cv2.imshow("result2", imS)
#cv2.imshow('mask', mask)
#cv2.imshow('thresh', thresh)
SortedCubes = sortNumbers(Cubes)
print("\nFound array [x, y, Cube_num] = ", Cubes)
print("Sorted array [x, y, Cube_num] = ", SortedCubes)
cv2.waitKey(0)
cv2.destroyAllWindows()
I get the following error (it can't detect a number)
Traceback (most recent call last): File "c:/Users/Mads/OneDrive/Universitet/7. semester/ROB1/python/objectDetectiong.py", line 169, in <module> result = getNumber('ROI_{}.png'.format(ROI_number)) File "c:/Users/Mads/OneDrive/Universitet/7. semester/ROB1/python/objectDetectiong.py", line 70, in getNumber predicted_digit = result[0][1] IndexError: list index out of range

This is implementation of my comment. Since, I do not have individual images this code will work with given grid like processed image.
For OCR I used EasyOCR instead of Tesserect. You could also try pytesserect on each output cropped images. Instead of rotating 4 times by 90 degrees by confidence, I went with digit detection on OCR result. If a detection is not a number then only rotate and retry.
Tested on google colab. Replace cv2_imshow(...) with cv2.imshow(...) for working locally. Also remove from google.colab.patches import cv2_imshow import.
This is modified version of my answer on card orientation correction here, OpenCV: using Canny and Shi-Tomasi to detect round corners of a playing card. All previous code is left as comment.
Code
!pip install easyocr
import easyocr
reader = easyocr.Reader(['ch_sim','en']) # need to run only once to load model into memory
"""
Based on my answer of rotated card detection,
https://stackoverflow.com/questions/64860785/opencv-using-canny-and-shi-tomasi-to-detect-round-corners-of-a-playing-card/64862448#64862448
"""
import cv2
import numpy as np
from google.colab.patches import cv2_imshow
img = cv2.imread('1.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(gray,127,255,0)
#cv2_imshow(thresh)
#cv2.imshow('Thresholded original',thresh)
#cv2.waitKey(0)
## Get contours
contours,h = cv2.findContours(thresh,cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
## only draw contour that have big areas
imx = img.shape[0]
imy = img.shape[1]
lp_area = (imx * imy) / 10
#################################################################
# Four point perspective transform
# https://www.pyimagesearch.com/2014/08/25/4-point-opencv-getperspective-transform-example/
#################################################################
def order_points(pts):
# initialzie a list of coordinates that will be ordered
# such that the first entry in the list is the top-left,
# the second entry is the top-right, the third is the
# bottom-right, and the fourth is the bottom-left
rect = np.zeros((4, 2), dtype = "float32")
# the top-left point will have the smallest sum, whereas
# the bottom-right point will have the largest sum
s = pts.sum(axis = 1)
rect[0] = pts[np.argmin(s)]
rect[2] = pts[np.argmax(s)]
# now, compute the difference between the points, the
# top-right point will have the smallest difference,
# whereas the bottom-left will have the largest difference
diff = np.diff(pts, axis = 1)
rect[1] = pts[np.argmin(diff)]
rect[3] = pts[np.argmax(diff)]
# return the ordered coordinates
return rect
def four_point_transform(image, pts):
# obtain a consistent order of the points and unpack them
# individually
rect = order_points(pts)
(tl, tr, br, bl) = rect
# compute the width of the new image, which will be the
# maximum distance between bottom-right and bottom-left
# x-coordiates or the top-right and top-left x-coordinates
widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
maxWidth = max(int(widthA), int(widthB))
# compute the height of the new image, which will be the
# maximum distance between the top-right and bottom-right
# y-coordinates or the top-left and bottom-left y-coordinates
heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
maxHeight = max(int(heightA), int(heightB))
# now that we have the dimensions of the new image, construct
# the set of destination points to obtain a "birds eye view",
# (i.e. top-down view) of the image, again specifying points
# in the top-left, top-right, bottom-right, and bottom-left
# order
dst = np.array([
[0, 0],
[maxWidth - 1, 0],
[maxWidth - 1, maxHeight - 1],
[0, maxHeight - 1]], dtype = "float32")
# compute the perspective transform matrix and then apply it
M = cv2.getPerspectiveTransform(rect, dst)
warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))
# return the warped image
return warped
#################################################################
#print(len(contours))
tmp_img = img.copy()
for cnt in contours:
approx = cv2.approxPolyDP(cnt,0.01 * cv2.arcLength(cnt, True), True)
## calculate number of vertices
#print(len(approx))
## Get the largest contours only
## Side count cannot be used since contours are not all rectangular
if cv2.contourArea(cnt) > lp_area:
#if len(approx) == 4 and cv2.contourArea(cnt) > lp_area:
# print("\n\n")
# print("#################################################")
# print("rectangle")
# print("#################################################")
# print("\n\n")
#tmp_img = img.copy()
#cv2.drawContours(tmp_img, [cnt], 0, (0, 255, 0), 6)
#cv2_imshow(tmp_img)
#cv2.imshow('Contour Borders', tmp_img)
#cv2.waitKey(0)
# tmp_img = img.copy()
# cv2.drawContours(tmp_img, [cnt], 0, (255, 0, 255), -1)
# cv2_imshow(tmp_img)
# #cv2.imshow('Contour Filled', tmp_img)
# #cv2.waitKey(0)
# # Make a hull arround the contour and draw it on the original image
# tmp_img = img.copy()
# mask = np.zeros((img.shape[:2]), np.uint8)
# hull = cv2.convexHull(cnt)
# cv2.drawContours(mask, [hull], 0, (255, 255, 255), -1)
# cv2_imshow(mask)
# #cv2.imshow('Convex Hull Mask', mask)
# #cv2.waitKey(0)
# # Draw minimum area rectangle
# #tmp_img = img.copy()
# rect = cv2.minAreaRect(cnt)
# box = cv2.boxPoints(rect)
# box = np.int0(box)
# cv2.drawContours(tmp_img, [box], 0, (255, 0, 0), 2)
# #cv2_imshow(tmp_img)
# #cv2.imshow('Minimum Area Rectangle', tmp_img)
# #cv2.waitKey(0)
# Draw box corners and minimum area rectangle
#tmp_img = img.copy()
rect = cv2.minAreaRect(cnt)
box = cv2.boxPoints(rect)
box = np.int0(box)
#print(rect)
#print(box)
cv2.drawContours(tmp_img, [box], 0, (0, 50, 255), 3)
cv2.circle(tmp_img, tuple(box[0]), 8, (0, 255, 0), -1)
cv2.circle(tmp_img, tuple(box[1]), 8, (0, 255, 0), -1)
cv2.circle(tmp_img, tuple(box[2]), 8, (0, 255, 0), -1)
cv2.circle(tmp_img, tuple(box[3]), 8, (0, 255, 0), -1)
#cv2_imshow(tmp_img)
#cv2.imshow('Minimum Area Rectangle', tmp_img)
#cv2.waitKey(0)
## Correct orientation and crop
# Link, https://jdhao.github.io/2019/02/23/crop_rotated_rectangle_opencv/
width = int(rect[1][0])
height = int(rect[1][1])
src_pts = box.astype("float32")
dst_pts = np.array([[0, height-1],
[0, 0],
[width-1, 0],
[width-1, height-1]], dtype="float32")
M = cv2.getPerspectiveTransform(src_pts, dst_pts)
warped = cv2.warpPerspective(img, M, (width, height))
#cv2_imshow(warped)
# Run OCR on cropped image
# If the predicted value is digit print else rotate first
result = reader.readtext(warped)
predicted_digit = result[0][1]
print("Detected Text:")
if np.char.isdigit(predicted_digit) == True:
print(result)
print(predicted_digit)
cv2_imshow(warped)
else:
rot_img = warped.copy()
for i in range(0, 3):
rotated_image = cv2.rotate(rot_img, cv2.cv2.ROTATE_90_CLOCKWISE)
result = reader.readtext(rotated_image)
#if np.array(result).size == 0:
# continue
if not result:
rot_img = rotated_image
continue
#if len(result) == 0:
# continue
predicted_digit = result[0][1]
#print(result)
#print(predicted_digit)
#cv2_imshow(rotated_image)
if np.char.isdigit(predicted_digit) == True:
print(result)
print(predicted_digit)
cv2_imshow(rotated_image)
break
rot_img = rotated_image
# # Draw bounding rectangle
# #tmp_img = img.copy()
# x, y, w, h = cv2.boundingRect(cnt)
# cv2.rectangle(tmp_img, (x, y), (x + w, y + h), (255, 0, 0), 2)
# #cv2_imshow(tmp_img)
# #cv2.imshow('Bounding Rectangle', tmp_img)
# #cv2.waitKey(0)
# # Bounding Rectangle and Minimum Area Rectangle
# #tmp_img = img.copy()
# rect = cv2.minAreaRect(cnt)
# box = cv2.boxPoints(rect)
# box = np.int0(box)
# cv2.drawContours(tmp_img, [box], 0, (0, 0, 255), 2)
# x, y, w, h = cv2.boundingRect(cnt)
# cv2.rectangle(tmp_img, (x, y), (x + w, y + h), (0, 255, 0), 2)
# #cv2_imshow(tmp_img)
# #cv2.imshow('Bounding Rectangle', tmp_img)
# #cv2.waitKey(0)
# # determine the most extreme points along the contour
# # https://www.pyimagesearch.com/2016/04/11/finding-extreme-points-in-contours-with-opencv/
# tmp_img = img.copy()
# extLeft = tuple(cnt[cnt[:, :, 0].argmin()][0])
# extRight = tuple(cnt[cnt[:, :, 0].argmax()][0])
# extTop = tuple(cnt[cnt[:, :, 1].argmin()][0])
# extBot = tuple(cnt[cnt[:, :, 1].argmax()][0])
# cv2.drawContours(tmp_img, [cnt], -1, (0, 255, 255), 2)
# cv2.circle(tmp_img, extLeft, 8, (0, 0, 255), -1)
# cv2.circle(tmp_img, extRight, 8, (0, 255, 0), -1)
# cv2.circle(tmp_img, extTop, 8, (255, 0, 0), -1)
# cv2.circle(tmp_img, extBot, 8, (255, 255, 0), -1)
# print("Corner Points: ", extLeft, extRight, extTop, extBot)
# cv2_imshow(tmp_img)
# #cv2.imshow('img contour drawn', tmp_img)
# #cv2.waitKey(0)
# #cv2.destroyAllWindows()
# ## Perspective Transform
# tmp_img = img.copy()
# pts = np.array([extLeft, extRight, extTop, extBot])
# warped = four_point_transform(tmp_img, pts)
# cv2_imshow(tmp_img)
# #cv2.imshow("Warped", warped)
# #cv2.waitKey(0)
cv2_imshow(tmp_img)
#cv2.destroyAllWindows()
Output Prediction
Detected Text:
[([[85, 67], [131, 67], [131, 127], [85, 127]], '1', 0.9992043972015381)]
1
Detected Text:
[([[85, 65], [133, 65], [133, 125], [85, 125]], '2', 0.9991914629936218)]
2
Detected Text:
[([[96, 72], [144, 72], [144, 128], [96, 128]], '4', 0.9996564984321594)]
4
Detected Text:
[([[88, 76], [132, 76], [132, 132], [88, 132]], '3', 0.9973381161689758)]
3
White Region Detection With Corners
Alternate methods,
Try pretrained digit classification model trained from MNIST and others on each large contours exceeding certain area.
Use multitask object detection with rotation. One output of network will be detections another angle regression to predict orientation.
Use text detector like, East and run OCR on each detected text.

draw multiple transparent masks on an image

I have an image and some binary masks I want to apply to the image to highlight certain areas. I'm able to draw one mask, but each subsequent applied mask lightens the previous mask and the original image more and more.
How can I apply multiple masks while keeping each mask and the image brightness constant?
import numpy as np
import matplotlib
from matplotlib.pyplot import imshow
from PIL import Image, ImageDraw, ImageFont
import requests
matplotlib.rcParams['figure.figsize'] = (20.0, 10.0)
url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/e/ee/Grumpy_Cat_by_Gage_Skidmore.jpg/480px-Grumpy_Cat_by_Gage_Skidmore.jpg'
image = (Image.open(requests.get(url, stream=True).raw)).convert('RGBA')
annotation1 = (np.ones((image.size[1], image.size[0], 3))*255).astype(np.uint8)
annotation1[350:400, 50:450] = (255, 0, 0)
mask1 = (np.zeros((image.size[1], image.size[0])))
mask1[350:400, 50:450] = 1
mask1 = Image.fromarray(mask1, mode='1')
annotation2 = (np.ones((image.size[1], image.size[0], 3))*255).astype(np.uint8)
annotation2[400:450, 50:450] = (255, 0, 0)
mask2 = (np.zeros((image.size[1], image.size[0])))
mask2[350:400, 50:450] = 1
mask2 = Image.fromarray(mask2, mode='1')
annotation1 = Image.fromarray(annotation1, mode='RGB').convert('RGBA')
annotation2 = Image.fromarray(annotation2, mode='RGB').convert('RGBA')
annotation1.putalpha(128)
annotation2.putalpha(128)
image = Image.alpha_composite(image, annotation1)
image = Image.alpha_composite(image, annotation2)
imshow(image)
I have also tried using Image.composite(), but it only shows the mask and whites out the rest of the image.
image = Image.composite(image, annotation1, mask1)

You can use ImageDraw.bitmap(xy, bitmap, fill=None) to draw masks from bitmaps. You can have multiple shades per mask, but only one color.
url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/e/ee/Grumpy_Cat_by_Gage_Skidmore.jpg/480px-Grumpy_Cat_by_Gage_Skidmore.jpg'
image = (Image.open(requests.get(url, stream=True).raw)).convert('RGBA')
image.putalpha(128)
mask1 = (np.zeros((image.size[1], image.size[0]))).astype(np.uint8)
mask1[350:400, 50:450] = 255
mask1 = Image.fromarray(mask1, mode='L')
mask2 = (np.zeros((image.size[1], image.size[0]))).astype(np.uint8)
mask2[410:460, 50:450] = 255
mask2[415:455, 55:445] = 128
mask2 = Image.fromarray(mask2, mode='L')
overlay = Image.new('RGBA', image.size, (255,255,255,0))
drawing = ImageDraw.Draw(overlay)
drawing.bitmap((0, 0), mask1, fill=(255, 0, 0, 128))
drawing.bitmap((0, 0), mask2, fill=(255, 0, 0, 128))
image = Image.alpha_composite(image, overlay)
imshow(image)

Cropping Concave polygon from Image using Opencv python

How can I crop a concave polygon from an image. My Input image look like
.
and the coordinates of closed polygon are
[10,150],[150,100],[300,150],[350,100],[310,20],[35,10]. I want region bounded by concave polygon to be cropped using opencv. I searched for other similar questions but I did not able to find correct answer. That's why I am asking it ? Can you help me.
Any help would be highly appreciated.!!!

Steps
find region using the poly points
create mask using the poly points
do mask op to crop
add white bg if needed
The code:
# 2018.01.17 20:39:17 CST
# 2018.01.17 20:50:35 CST
import numpy as np
import cv2
img = cv2.imread("test.png")
pts = np.array([[10,150],[150,100],[300,150],[350,100],[310,20],[35,10]])
## (1) Crop the bounding rect
rect = cv2.boundingRect(pts)
x,y,w,h = rect
croped = img[y:y+h, x:x+w].copy()
## (2) make mask
pts = pts - pts.min(axis=0)
mask = np.zeros(croped.shape[:2], np.uint8)
cv2.drawContours(mask, [pts], -1, (255, 255, 255), -1, cv2.LINE_AA)
## (3) do bit-op
dst = cv2.bitwise_and(croped, croped, mask=mask)
## (4) add the white background
bg = np.ones_like(croped, np.uint8)*255
cv2.bitwise_not(bg,bg, mask=mask)
dst2 = bg+ dst
cv2.imwrite("croped.png", croped)
cv2.imwrite("mask.png", mask)
cv2.imwrite("dst.png", dst)
cv2.imwrite("dst2.png", dst2)
Source image:
Result:

You can do it in 3 steps:
Create a mask out of the image
mask = np.zeros((height, width))
points = np.array([[[10,150],[150,100],[300,150],[350,100],[310,20],[35,10]]])
cv2.fillPoly(mask, points, (255))
Apply mask to original image
res = cv2.bitwise_and(img,img,mask = mask)
Optionally you can remove the crop the image to have a smaller one
rect = cv2.boundingRect(points) # returns (x,y,w,h) of the rect
cropped = res[rect[1]: rect[1] + rect[3], rect[0]: rect[0] + rect[2]]
With this you should have at the end the image cropped
UPDATE
For the sake of completeness here is the complete code:
import numpy as np
import cv2
img = cv2.imread("test.png")
height = img.shape[0]
width = img.shape[1]
mask = np.zeros((height, width), dtype=np.uint8)
points = np.array([[[10,150],[150,100],[300,150],[350,100],[310,20],[35,10]]])
cv2.fillPoly(mask, points, (255))
res = cv2.bitwise_and(img,img,mask = mask)
rect = cv2.boundingRect(points) # returns (x,y,w,h) of the rect
cropped = res[rect[1]: rect[1] + rect[3], rect[0]: rect[0] + rect[2]]
cv2.imshow("cropped" , cropped )
cv2.imshow("same size" , res)
cv2.waitKey(0)
For the colored background version use the code like this:
import numpy as np
import cv2
img = cv2.imread("test.png")
height = img.shape[0]
width = img.shape[1]
mask = np.zeros((height, width), dtype=np.uint8)
points = np.array([[[10,150],[150,100],[300,150],[350,100],[310,20],[35,10]]])
cv2.fillPoly(mask, points, (255))
res = cv2.bitwise_and(img,img,mask = mask)
rect = cv2.boundingRect(points) # returns (x,y,w,h) of the rect
im2 = np.full((res.shape[0], res.shape[1], 3), (0, 255, 0), dtype=np.uint8 ) # you can also use other colors or simply load another image of the same size
maskInv = cv2.bitwise_not(mask)
colorCrop = cv2.bitwise_or(im2,im2,mask = maskInv)
finalIm = res + colorCrop
cropped = finalIm[rect[1]: rect[1] + rect[3], rect[0]: rect[0] + rect[2]]
cv2.imshow("cropped" , cropped )
cv2.imshow("same size" , res)
cv2.waitKey(0)

For the blured image background version use the code like this:
img = cv2.imread(img_path)
box = <box points>
# -- background
blur_bg = cv2.blur(img, (h, w))
mask1 = np.zeros((h, w, 3), np.uint8)
mask2 = np.ones((h, w, 3), np.uint8) * 255
cv2.fillPoly(mask1, box, (255, 255, 255))
# -- indexing
img_idx = np.where(mask1 == mask2)
bg_idx = np.where(mask1 != mask2)
# -- fill box
res = np.zeros((h, w, 3), np.int64)
res[img_idx] = img[img_idx]
res[bg_idx] = blur_bg[bg_idx]
res = res[y1:y2, x1:x2, :]