如何合并附近的边界框 OpenCV
How to merge nearby bounding boxes OpenCV
我正在尝试使用图像处理工具 (OpenCV) 将网页分割为页眉、页脚、左面板、右面板等（获取坐标），但结果并不令人满意。
我想得到这样的东西：
但是，我所得到的
import cv2
import numpy
from google.colab.patches import cv2_imshow
img = cv2.imread("test.png")
blue, green, red = cv2.split(img)
def medianCanny(img, thresh1, thresh2):
median = numpy.median(img)
img = cv2.Canny(img, int(thresh1 * median), int(thresh2 * median))
return img
blue_edges = medianCanny(blue, 0, 1)
green_edges = medianCanny(green, 0, 1)
red_edges = medianCanny(red, 0, 1)
edges = blue_edges | green_edges | red_edges
contours,hierarchy = cv2.findContours(edges, cv2.RETR_EXTERNAL ,cv2.CHAIN_APPROX_SIMPLE)
hierarchy = hierarchy[0]
for component in zip(contours, hierarchy):
currentContour = component[0]
currentHierarchy = component[1]
x,y,w,h = cv2.boundingRect(currentContour)
if currentHierarchy[3] < 0:
cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),1)
cv2_imshow(img)
cv2.waitKey(0)
cv2.destroyAllWindows()
我想连接附近的盒子，但我不知道怎么做最好。
Test image
我开始以您的代码为基础来获得绿色矩形。我按大小过滤框以去除包含大块图像的大框（甚至有一个围绕整个图像的框）。从那里开始，我反复合并附近的盒子，直到不再有重叠的盒子。我使用 merge_margin 变量来设置两个框在计算为“重叠”之前需要多近。
每一步（我突出显示了最后一个合并框和它在里面找到的点）
（这个 gif 被严重压缩，所以你会看到一些伪影）
最终图像
import cv2
import numpy as np
# tuplify
def tup(point):
return (point[0], point[1]);
# returns true if the two boxes overlap
def overlap(source, target):
# unpack points
tl1, br1 = source;
tl2, br2 = target;
# checks
if (tl1[0] >= br2[0] or tl2[0] >= br1[0]):
return False;
if (tl1[1] >= br2[1] or tl2[1] >= br1[1]):
return False;
return True;
# returns all overlapping boxes
def getAllOverlaps(boxes, bounds, index):
overlaps = [];
for a in range(len(boxes)):
if a != index:
if overlap(bounds, boxes[a]):
overlaps.append(a);
return overlaps;
img = cv2.imread("test.png")
orig = np.copy(img);
blue, green, red = cv2.split(img)
def medianCanny(img, thresh1, thresh2):
median = np.median(img)
img = cv2.Canny(img, int(thresh1 * median), int(thresh2 * median))
return img
blue_edges = medianCanny(blue, 0, 1)
green_edges = medianCanny(green, 0, 1)
red_edges = medianCanny(red, 0, 1)
edges = blue_edges | green_edges | red_edges
# I'm using OpenCV 3.4. This returns (contours, hierarchy) in OpenCV 2 and 4
_, contours,hierarchy = cv2.findContours(edges, cv2.RETR_EXTERNAL ,cv2.CHAIN_APPROX_SIMPLE)
# go through the contours and save the box edges
boxes = []; # each element is [[top-left], [bottom-right]];
hierarchy = hierarchy[0]
for component in zip(contours, hierarchy):
currentContour = component[0]
currentHierarchy = component[1]
x,y,w,h = cv2.boundingRect(currentContour)
if currentHierarchy[3] < 0:
cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),1)
boxes.append([[x,y], [x+w, y+h]]);
# filter out excessively large boxes
filtered = [];
max_area = 30000;
for box in boxes:
w = box[1][0] - box[0][0];
h = box[1][1] - box[0][1];
if w*h < max_area:
filtered.append(box);
boxes = filtered;
# go through the boxes and start merging
merge_margin = 20;
# this is gonna take a long time
finished = False;
highlight = [[0,0], [1,1]];
points = [[[0,0]]];
while not finished:
# set end con
finished = True;
# check progress
print("Len Boxes: " + str(len(boxes)));
# draw boxes # comment this section out to run faster
copy = np.copy(orig);
for box in boxes:
cv2.rectangle(copy, tup(box[0]), tup(box[1]), (0,200,0), 1);
cv2.rectangle(copy, tup(highlight[0]), tup(highlight[1]), (0,0,255), 2);
for point in points:
point = point[0];
cv2.circle(copy, tup(point), 4, (255,0,0), -1);
cv2.imshow("Copy", copy);
key = cv2.waitKey(1);
if key == ord('q'):
break;
# loop through boxes
index = 0;
while index < len(boxes):
# grab current box
curr = boxes[index];
# add margin
tl = curr[0][:];
br = curr[1][:];
tl[0] -= merge_margin;
tl[1] -= merge_margin;
br[0] += merge_margin;
br[1] += merge_margin;
# get matching boxes
overlaps = getAllOverlaps(boxes, [tl, br], index);
# check if empty
if len(overlaps) > 0:
# combine boxes
# convert to a contour
con = [];
overlaps.append(index);
for ind in overlaps:
tl, br = boxes[ind];
con.append([tl]);
con.append([br]);
con = np.array(con);
# get bounding rect
x,y,w,h = cv2.boundingRect(con);
# stop growing
w -= 1;
h -= 1;
merged = [[x,y], [x+w, y+h]];
# highlights
highlight = merged[:];
points = con;
# remove boxes from list
overlaps.sort(reverse = True);
for ind in overlaps:
del boxes[ind];
boxes.append(merged);
# set flag
finished = False;
break;
# increment
index += 1;
cv2.destroyAllWindows();
# show final
copy = np.copy(orig);
for box in boxes:
cv2.rectangle(copy, tup(box[0]), tup(box[1]), (0,200,0), 1);
cv2.imshow("Final", copy);
cv2.waitKey(0);
编辑：它的低效率让我有点困扰。盒子合并的顺序实际上没有意义。你可以看到有很多小盒子合并成一个大盒子的步骤，而不是一个大盒子吃掉它内部的所有东西并成长。事实证明这是一个非常简单的代码修复。由于新合并的框被附加到框列表的末尾，我们可以反向索引使其从大到小。
我将 merge_margin 更改为 15，因为我认为这更接近问题中的目标解决方案。
import cv2
import numpy as np
# tuplify
def tup(point):
return (point[0], point[1]);
# returns true if the two boxes overlap
def overlap(source, target):
# unpack points
tl1, br1 = source;
tl2, br2 = target;
# checks
if (tl1[0] >= br2[0] or tl2[0] >= br1[0]):
return False;
if (tl1[1] >= br2[1] or tl2[1] >= br1[1]):
return False;
return True;
# returns all overlapping boxes
def getAllOverlaps(boxes, bounds, index):
overlaps = [];
for a in range(len(boxes)):
if a != index:
if overlap(bounds, boxes[a]):
overlaps.append(a);
return overlaps;
img = cv2.imread("test.png")
orig = np.copy(img);
blue, green, red = cv2.split(img)
def medianCanny(img, thresh1, thresh2):
median = np.median(img)
img = cv2.Canny(img, int(thresh1 * median), int(thresh2 * median))
return img
blue_edges = medianCanny(blue, 0, 1)
green_edges = medianCanny(green, 0, 1)
red_edges = medianCanny(red, 0, 1)
edges = blue_edges | green_edges | red_edges
# I'm using OpenCV 3.4. This returns (contours, hierarchy) in OpenCV 2 and 4
_, contours,hierarchy = cv2.findContours(edges, cv2.RETR_EXTERNAL ,cv2.CHAIN_APPROX_SIMPLE)
# go through the contours and save the box edges
boxes = []; # each element is [[top-left], [bottom-right]];
hierarchy = hierarchy[0]
for component in zip(contours, hierarchy):
currentContour = component[0]
currentHierarchy = component[1]
x,y,w,h = cv2.boundingRect(currentContour)
if currentHierarchy[3] < 0:
cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),1)
boxes.append([[x,y], [x+w, y+h]]);
# filter out excessively large boxes
filtered = [];
max_area = 30000;
for box in boxes:
w = box[1][0] - box[0][0];
h = box[1][1] - box[0][1];
if w*h < max_area:
filtered.append(box);
boxes = filtered;
# go through the boxes and start merging
merge_margin = 15;
# this is gonna take a long time
finished = False;
highlight = [[0,0], [1,1]];
points = [[[0,0]]];
while not finished:
# set end con
finished = True;
# check progress
print("Len Boxes: " + str(len(boxes)));
# draw boxes # comment this section out to run faster
copy = np.copy(orig);
for box in boxes:
cv2.rectangle(copy, tup(box[0]), tup(box[1]), (0,200,0), 1);
cv2.rectangle(copy, tup(highlight[0]), tup(highlight[1]), (0,0,255), 2);
for point in points:
point = point[0];
cv2.circle(copy, tup(point), 4, (255,0,0), -1);
cv2.imshow("Copy", copy);
key = cv2.waitKey(1);
if key == ord('q'):
break;
# loop through boxes
index = len(boxes) - 1;
while index >= 0:
# grab current box
curr = boxes[index];
# add margin
tl = curr[0][:];
br = curr[1][:];
tl[0] -= merge_margin;
tl[1] -= merge_margin;
br[0] += merge_margin;
br[1] += merge_margin;
# get matching boxes
overlaps = getAllOverlaps(boxes, [tl, br], index);
# check if empty
if len(overlaps) > 0:
# combine boxes
# convert to a contour
con = [];
overlaps.append(index);
for ind in overlaps:
tl, br = boxes[ind];
con.append([tl]);
con.append([br]);
con = np.array(con);
# get bounding rect
x,y,w,h = cv2.boundingRect(con);
# stop growing
w -= 1;
h -= 1;
merged = [[x,y], [x+w, y+h]];
# highlights
highlight = merged[:];
points = con;
# remove boxes from list
overlaps.sort(reverse = True);
for ind in overlaps:
del boxes[ind];
boxes.append(merged);
# set flag
finished = False;
break;
# increment
index -= 1;
cv2.destroyAllWindows();
# show final
copy = np.copy(orig);
for box in boxes:
cv2.rectangle(copy, tup(box[0]), tup(box[1]), (0,200,0), 1);
cv2.imshow("Final", copy);
cv2.waitKey(0);
我正在尝试使用图像处理工具 (OpenCV) 将网页分割为页眉、页脚、左面板、右面板等（获取坐标），但结果并不令人满意。
我想得到这样的东西：
但是，我所得到的
import cv2
import numpy
from google.colab.patches import cv2_imshow
img = cv2.imread("test.png")
blue, green, red = cv2.split(img)
def medianCanny(img, thresh1, thresh2):
median = numpy.median(img)
img = cv2.Canny(img, int(thresh1 * median), int(thresh2 * median))
return img
blue_edges = medianCanny(blue, 0, 1)
green_edges = medianCanny(green, 0, 1)
red_edges = medianCanny(red, 0, 1)
edges = blue_edges | green_edges | red_edges
contours,hierarchy = cv2.findContours(edges, cv2.RETR_EXTERNAL ,cv2.CHAIN_APPROX_SIMPLE)
hierarchy = hierarchy[0]
for component in zip(contours, hierarchy):
currentContour = component[0]
currentHierarchy = component[1]
x,y,w,h = cv2.boundingRect(currentContour)
if currentHierarchy[3] < 0:
cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),1)
cv2_imshow(img)
cv2.waitKey(0)
cv2.destroyAllWindows()
我想连接附近的盒子，但我不知道怎么做最好。
Test image
我开始以您的代码为基础来获得绿色矩形。我按大小过滤框以去除包含大块图像的大框（甚至有一个围绕整个图像的框）。从那里开始，我反复合并附近的盒子，直到不再有重叠的盒子。我使用 merge_margin 变量来设置两个框在计算为“重叠”之前需要多近。
每一步（我突出显示了最后一个合并框和它在里面找到的点） （这个 gif 被严重压缩，所以你会看到一些伪影）
最终图像
import cv2
import numpy as np
# tuplify
def tup(point):
return (point[0], point[1]);
# returns true if the two boxes overlap
def overlap(source, target):
# unpack points
tl1, br1 = source;
tl2, br2 = target;
# checks
if (tl1[0] >= br2[0] or tl2[0] >= br1[0]):
return False;
if (tl1[1] >= br2[1] or tl2[1] >= br1[1]):
return False;
return True;
# returns all overlapping boxes
def getAllOverlaps(boxes, bounds, index):
overlaps = [];
for a in range(len(boxes)):
if a != index:
if overlap(bounds, boxes[a]):
overlaps.append(a);
return overlaps;
img = cv2.imread("test.png")
orig = np.copy(img);
blue, green, red = cv2.split(img)
def medianCanny(img, thresh1, thresh2):
median = np.median(img)
img = cv2.Canny(img, int(thresh1 * median), int(thresh2 * median))
return img
blue_edges = medianCanny(blue, 0, 1)
green_edges = medianCanny(green, 0, 1)
red_edges = medianCanny(red, 0, 1)
edges = blue_edges | green_edges | red_edges
# I'm using OpenCV 3.4. This returns (contours, hierarchy) in OpenCV 2 and 4
_, contours,hierarchy = cv2.findContours(edges, cv2.RETR_EXTERNAL ,cv2.CHAIN_APPROX_SIMPLE)
# go through the contours and save the box edges
boxes = []; # each element is [[top-left], [bottom-right]];
hierarchy = hierarchy[0]
for component in zip(contours, hierarchy):
currentContour = component[0]
currentHierarchy = component[1]
x,y,w,h = cv2.boundingRect(currentContour)
if currentHierarchy[3] < 0:
cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),1)
boxes.append([[x,y], [x+w, y+h]]);
# filter out excessively large boxes
filtered = [];
max_area = 30000;
for box in boxes:
w = box[1][0] - box[0][0];
h = box[1][1] - box[0][1];
if w*h < max_area:
filtered.append(box);
boxes = filtered;
# go through the boxes and start merging
merge_margin = 20;
# this is gonna take a long time
finished = False;
highlight = [[0,0], [1,1]];
points = [[[0,0]]];
while not finished:
# set end con
finished = True;
# check progress
print("Len Boxes: " + str(len(boxes)));
# draw boxes # comment this section out to run faster
copy = np.copy(orig);
for box in boxes:
cv2.rectangle(copy, tup(box[0]), tup(box[1]), (0,200,0), 1);
cv2.rectangle(copy, tup(highlight[0]), tup(highlight[1]), (0,0,255), 2);
for point in points:
point = point[0];
cv2.circle(copy, tup(point), 4, (255,0,0), -1);
cv2.imshow("Copy", copy);
key = cv2.waitKey(1);
if key == ord('q'):
break;
# loop through boxes
index = 0;
while index < len(boxes):
# grab current box
curr = boxes[index];
# add margin
tl = curr[0][:];
br = curr[1][:];
tl[0] -= merge_margin;
tl[1] -= merge_margin;
br[0] += merge_margin;
br[1] += merge_margin;
# get matching boxes
overlaps = getAllOverlaps(boxes, [tl, br], index);
# check if empty
if len(overlaps) > 0:
# combine boxes
# convert to a contour
con = [];
overlaps.append(index);
for ind in overlaps:
tl, br = boxes[ind];
con.append([tl]);
con.append([br]);
con = np.array(con);
# get bounding rect
x,y,w,h = cv2.boundingRect(con);
# stop growing
w -= 1;
h -= 1;
merged = [[x,y], [x+w, y+h]];
# highlights
highlight = merged[:];
points = con;
# remove boxes from list
overlaps.sort(reverse = True);
for ind in overlaps:
del boxes[ind];
boxes.append(merged);
# set flag
finished = False;
break;
# increment
index += 1;
cv2.destroyAllWindows();
# show final
copy = np.copy(orig);
for box in boxes:
cv2.rectangle(copy, tup(box[0]), tup(box[1]), (0,200,0), 1);
cv2.imshow("Final", copy);
cv2.waitKey(0);
编辑：它的低效率让我有点困扰。盒子合并的顺序实际上没有意义。你可以看到有很多小盒子合并成一个大盒子的步骤，而不是一个大盒子吃掉它内部的所有东西并成长。事实证明这是一个非常简单的代码修复。由于新合并的框被附加到框列表的末尾，我们可以反向索引使其从大到小。
我将 merge_margin 更改为 15，因为我认为这更接近问题中的目标解决方案。
import cv2
import numpy as np
# tuplify
def tup(point):
return (point[0], point[1]);
# returns true if the two boxes overlap
def overlap(source, target):
# unpack points
tl1, br1 = source;
tl2, br2 = target;
# checks
if (tl1[0] >= br2[0] or tl2[0] >= br1[0]):
return False;
if (tl1[1] >= br2[1] or tl2[1] >= br1[1]):
return False;
return True;
# returns all overlapping boxes
def getAllOverlaps(boxes, bounds, index):
overlaps = [];
for a in range(len(boxes)):
if a != index:
if overlap(bounds, boxes[a]):
overlaps.append(a);
return overlaps;
img = cv2.imread("test.png")
orig = np.copy(img);
blue, green, red = cv2.split(img)
def medianCanny(img, thresh1, thresh2):
median = np.median(img)
img = cv2.Canny(img, int(thresh1 * median), int(thresh2 * median))
return img
blue_edges = medianCanny(blue, 0, 1)
green_edges = medianCanny(green, 0, 1)
red_edges = medianCanny(red, 0, 1)
edges = blue_edges | green_edges | red_edges
# I'm using OpenCV 3.4. This returns (contours, hierarchy) in OpenCV 2 and 4
_, contours,hierarchy = cv2.findContours(edges, cv2.RETR_EXTERNAL ,cv2.CHAIN_APPROX_SIMPLE)
# go through the contours and save the box edges
boxes = []; # each element is [[top-left], [bottom-right]];
hierarchy = hierarchy[0]
for component in zip(contours, hierarchy):
currentContour = component[0]
currentHierarchy = component[1]
x,y,w,h = cv2.boundingRect(currentContour)
if currentHierarchy[3] < 0:
cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),1)
boxes.append([[x,y], [x+w, y+h]]);
# filter out excessively large boxes
filtered = [];
max_area = 30000;
for box in boxes:
w = box[1][0] - box[0][0];
h = box[1][1] - box[0][1];
if w*h < max_area:
filtered.append(box);
boxes = filtered;
# go through the boxes and start merging
merge_margin = 15;
# this is gonna take a long time
finished = False;
highlight = [[0,0], [1,1]];
points = [[[0,0]]];
while not finished:
# set end con
finished = True;
# check progress
print("Len Boxes: " + str(len(boxes)));
# draw boxes # comment this section out to run faster
copy = np.copy(orig);
for box in boxes:
cv2.rectangle(copy, tup(box[0]), tup(box[1]), (0,200,0), 1);
cv2.rectangle(copy, tup(highlight[0]), tup(highlight[1]), (0,0,255), 2);
for point in points:
point = point[0];
cv2.circle(copy, tup(point), 4, (255,0,0), -1);
cv2.imshow("Copy", copy);
key = cv2.waitKey(1);
if key == ord('q'):
break;
# loop through boxes
index = len(boxes) - 1;
while index >= 0:
# grab current box
curr = boxes[index];
# add margin
tl = curr[0][:];
br = curr[1][:];
tl[0] -= merge_margin;
tl[1] -= merge_margin;
br[0] += merge_margin;
br[1] += merge_margin;
# get matching boxes
overlaps = getAllOverlaps(boxes, [tl, br], index);
# check if empty
if len(overlaps) > 0:
# combine boxes
# convert to a contour
con = [];
overlaps.append(index);
for ind in overlaps:
tl, br = boxes[ind];
con.append([tl]);
con.append([br]);
con = np.array(con);
# get bounding rect
x,y,w,h = cv2.boundingRect(con);
# stop growing
w -= 1;
h -= 1;
merged = [[x,y], [x+w, y+h]];
# highlights
highlight = merged[:];
points = con;
# remove boxes from list
overlaps.sort(reverse = True);
for ind in overlaps:
del boxes[ind];
boxes.append(merged);
# set flag
finished = False;
break;
# increment
index -= 1;
cv2.destroyAllWindows();
# show final
copy = np.copy(orig);
for box in boxes:
cv2.rectangle(copy, tup(box[0]), tup(box[1]), (0,200,0), 1);
cv2.imshow("Final", copy);
cv2.waitKey(0);