I am doing a college class project on image processing. This is my original image:
I want to join nearby/overlapping bounding boxes on individual text line images, but I don't know how. My code looks like this so far (thanks to @HansHirse for the help):
import os
import cv2
import numpy as np
from scipy import stats
image = cv2.imread('example.png')
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(gray,127,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
#dilation
kernel = np.ones((5,5), np.uint8)
img_dilation = cv2.dilate(thresh, kernel, iterations=1)
#find contours
ctrs, hier = cv2.findContours(img_dilation.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# https://www.pyimagesearch.com/2015/04/20/sorting-contours-using-python-and-opencv/
def sort_contours(cnts, method="left-to-right"):
# initialize the reverse flag and sort index
reverse = False
i = 0
# handle if we need to sort in reverse
if method == "right-to-left" or method == "bottom-to-top":
reverse = True
# handle if we are sorting against the y-coordinate rather than
# the x-coordinate of the bounding box
if method == "top-to-bottom" or method == "bottom-to-top":
i = 1
# construct the list of bounding boxes and sort them from top to
# bottom
boundingBoxes = [cv2.boundingRect(c) for c in cnts]
(cnts, boundingBoxes) = zip(*sorted(zip(cnts, boundingBoxes),
key=lambda b: b[1][i], reverse=reverse))
# return the list of sorted contours and bounding boxes
return (cnts, boundingBoxes)
sortedctrs,sortedbbs=sort_contours(ctrs)
xyminmax=[]
for cnt in sortedctrs:
x, y, w, h = cv2.boundingRect(cnt)
xyminmax.append([x,y,x+w,y+h])
distances=[]
for i in range(len(xyminmax)):
try:
first_xmax = xyminmax[i][2]
second_xmin = xyminmax[i + 1][0]
distance=abs(second_xmin-first_xmax)
distances.append(distance)
except IndexError:
pass
THRESHOLD=stats.mode(distances, axis=None)[0][0]
new_rects=[]
for i in range(len(xyminmax)):
try:
# [xmin,ymin,xmax,ymax]
first_ymin=xyminmax[i][1]
first_ymax=xyminmax[i][3]
second_ymin=xyminmax[i+1][1]
second_ymax=xyminmax[i+1][3]
first_xmax = xyminmax[i][2]
second_xmin = xyminmax[i+1][0]
firstheight=abs(first_ymax-first_ymin)
secondheight=abs(second_ymax-second_ymin)
distance=abs(second_xmin-first_xmax)
if distance<THRESHOLD:
new_xmin=xyminmax[i][0]
new_xmax=xyminmax[i+1][2]
if first_ymin>second_ymin:
new_ymin=second_ymin
else:
new_ymin = first_ymin
if firstheight>secondheight:
new_ymax = first_ymax
else:
new_ymax = second_ymax
new_rects.append([new_xmin,new_ymin,new_xmax,new_ymax])
else:
new_rects.append(xyminmax[i])
except IndexError:
pass
for rect in new_rects:
cv2.rectangle(image, (rect[0], rect[1]), (rect[2], rect[3]), (121, 11, 189), 2)
cv2.imwrite("result.png",image)
which produces this image as a result:
I want to join very close or overlapping bounding boxes such as these
into a single bounding box so the formula doesn't get separated into single characters. I have tried using cv2.groupRectangles
but the print
results were just NULL
.
So, here comes my solution. I partially modified your (initial) code to my preferred naming, etc. Also, I commented all the stuff, I added.
import cv2
import numpy as np
image = cv2.imread('images/example.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
kernel = np.ones((5, 5), np.uint8)
img_dilated = cv2.dilate(thresh, kernel, iterations = 1)
cnts, _ = cv2.findContours(img_dilated.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# Array of initial bounding rects
rects = []
# Bool array indicating which initial bounding rect has
# already been used
rectsUsed = []
# Just initialize bounding rects and set all bools to false
for cnt in cnts:
rects.append(cv2.boundingRect(cnt))
rectsUsed.append(False)
# Sort bounding rects by x coordinate
def getXFromRect(item):
return item[0]
rects.sort(key = getXFromRect)
# Array of accepted rects
acceptedRects = []
# Merge threshold for x coordinate distance
xThr = 5
# Iterate all initial bounding rects
for supIdx, supVal in enumerate(rects):
if (rectsUsed[supIdx] == False):
# Initialize current rect
currxMin = supVal[0]
currxMax = supVal[0] + supVal[2]
curryMin = supVal[1]
curryMax = supVal[1] + supVal[3]
# This bounding rect is used
rectsUsed[supIdx] = True
# Iterate all initial bounding rects
# starting from the next
for subIdx, subVal in enumerate(rects[(supIdx+1):], start = (supIdx+1)):
# Initialize merge candidate
candxMin = subVal[0]
candxMax = subVal[0] + subVal[2]
candyMin = subVal[1]
candyMax = subVal[1] + subVal[3]
# Check if x distance between current rect
# and merge candidate is small enough
if (candxMin <= currxMax + xThr):
# Reset coordinates of current rect
currxMax = candxMax
curryMin = min(curryMin, candyMin)
curryMax = max(curryMax, candyMax)
# Merge candidate (bounding rect) is used
rectsUsed[subIdx] = True
else:
break
# No more merge candidates possible, accept current rect
acceptedRects.append([currxMin, curryMin, currxMax - currxMin, curryMax - curryMin])
for rect in acceptedRects:
img = cv2.rectangle(image, (rect[0], rect[1]), (rect[0] + rect[2], rect[1] + rect[3]), (121, 11, 189), 2)
cv2.imwrite("images/result.png", image)
For your example
I get the following output
Now, you have to find a proper threshold to meet your expectations. Maybe, there is even some more work to do, especially to get the whole formula, since the distances don't vary that much.
Disclaimer: I'm new to Python in general, and specially to the Python API of OpenCV (C++ for the win). Comments, improvements, highlighting Python no-gos are highly welcome!
Here is a slightly different approach, using the OpenCV Wrapper library .
import cv2
import opencv_wrapper as cvw
image = cv2.imread("example.png")
gray = cvw.bgr2gray(image)
thresh = cvw.threshold_otsu(gray, inverse=True)
# dilation
img_dilation = cvw.dilate(thresh, 5)
# Find contours
contours = cvw.find_external_contours(img_dilation)
# Map contours to bounding rectangles, using bounding_rect property
rects = map(lambda c: c.bounding_rect, contours)
# Sort rects by top-left x (rect.x == rect.tl.x)
sorted_rects = sorted(rects, key=lambda r: r.x)
# Distance threshold
dt = 5
# List of final, joined rectangles
final_rects = [sorted_rects[0]]
for rect in sorted_rects[1:]:
prev_rect = final_rects[-1]
# Shift rectangle `dt` back, to find out if they overlap
shifted_rect = cvw.Rect(rect.tl.x - dt, rect.tl.y, rect.width, rect.height)
intersection = cvw.rect_intersection(prev_rect, shifted_rect)
if intersection is not None:
# Join the two rectangles
min_y = min((prev_rect.tl.y, rect.tl.y))
max_y = max((prev_rect.bl.y, rect.bl.y))
max_x = max((prev_rect.br.x, rect.br.x))
width = max_x - prev_rect.tl.x
height = max_y - min_y
new_rect = cvw.Rect(prev_rect.tl.x, min_y, width, height)
# Add new rectangle to final list, making it the new prev_rect
# in the next iteration
final_rects[-1] = new_rect
else:
# If no intersection, add the box
final_rects.append(rect)
for rect in sorted_rects:
cvw.rectangle(image, rect, cvw.Color.MAGENTA, line_style=cvw.LineStyle.DASHED)
for rect in final_rects:
cvw.rectangle(image, rect, cvw.Color.GREEN, thickness=2)
cv2.imwrite("result.png", image)
The green boxes are the final result, while the magenta boxes are the original ones.
I used the same threshold as @HansHirse.
The equals sign still needs some work. Either a higher dilation kernel size or use the same technique vertically.
Disclosure: I am the author of OpenCV Wrapper.
Easy-to-read solution:
contours = get_contours(frame)
boxes = [cv2.boundingRect(c) for c in contours]
boxes = merge_boxes(boxes, x_val=40, y_val=20) # Where x_val and y_val are axis thresholds
def get_contours(frame): # Returns a list of contours
contours = cv2.findContours(frame, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = imutils.grab_contours(contours)
return contours
def merge_boxes(boxes, x_val, y_val):
size = len(boxes)
if size < 2:
return boxes
if size == 2:
if boxes_mergeable(boxes[0], boxes[1], x_val, y_val):
boxes[0] = union(boxes[0], boxes[1])
del boxes[1]
return boxes
boxes = sorted(boxes, key=lambda r: r[0])
i = size - 2
while i >= 0:
if boxes_mergeable(boxes[i], boxes[i + 1], x_val, y_val):
boxes[i] = union(boxes[i], boxes[i + 1])
del boxes[i + 1]
i -= 1
return boxes
def boxes_mergeable(box1, box2, x_val, y_val):
(x1, y1, w1, h1) = box1
(x2, y2, w2, h2) = box2
return max(x1, x2) - min(x1, x2) - minx_w(x1, w1, x2, w2) < x_val \
and max(y1, y2) - min(y1, y2) - miny_h(y1, h1, y2, h2) < y_val
def minx_w(x1, w1, x2, w2):
return w1 if x1 <= x2 else w2
def miny_h(y1, h1, y2, h2):
return h1 if y1 <= y2 else h2
def union(a, b):
x = min(a[0], b[0])
y = min(a[1], b[1])
w = max(a[0] + a[2], b[0] + b[2]) - x
h = max(a[1] + a[3], b[1] + b[3]) - y
return x, y, w, h
--> If you have bounding boxes and want to merge along both X and Y directions, use this snippet
--> Adjust x_pixel_value and y_pixel_value to your preferences
--> But for this, you need to have the bounding boxes
import cv2
img = cv2.imread(your image path)
x_pixel_value = 5
y_pixel_value = 6
bboxes_list = [] # your bounding boxes list
rects_used = []
for i in bboxes_list:
rects_used.append(False)
end_bboxes_list = []
for enum,i in enumerate(bboxes_list):
if rects_used[enum] == True:
continue
xmin = i[0]
xmax = i[2]
ymin = i[1]
ymax = i[3]
for enum1,j in enumerate(bboxes_list[(enum+1):], start = (enum+1)):
i_xmin = j[0]
i_xmax = j[2]
i_ymin = j[1]
i_ymax = j[3]
if rects_used[enum1] == False:
if abs(ymin - i_ymin) < x_pixel_value:
if abs(xmin-i_xmax) < y_pixel_value or abs(xmax-i_xmin) < y_pixel_value:
rects_used[enum1] = True
xmin = min(xmin,i_xmin)
xmax = max(xmax,i_xmax)
ymin = min(ymin,i_ymin)
ymax = max(ymax,i_ymax)
final_box = [xmin,ymin,xmax,ymax]
end_bboxes_list.append(final_box)
for i in end_bboxes_list:
cv2.rectangle(img,(i[0],i[1]),(i[2],i[3]), color = [0,255,0], thickness = 2)
cv2.imshow("Image",img)
cv2.waitKey(10000)
cv2.destroyAllWindows()
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.