[英]How to extract arbitrary background rectangular patches from an image with many different foregrounds
我正在使用FDDB-DataSet從同一圖像中提取人臉和相同數量的背景。
我能夠得到面孔(從注釋的坐標)。
我的問題是:我想用相同數量的人臉(不一定相同大小)裁剪 bacground 補丁,背景的限制是:
示例圖像:
注釋數據:
[Rmax Rmin theta Xc Yc]
[[ 52 38 1 154 72]
[ 57 38 -2 368 103]
[ 14 9 -2 11 64]
[ 11 8 1 29 16]
[ 10 6 1 56 61]
[ 10 6 -2 68 66]
[ 14 9 1 46 126]
[ 15 11 1 21 192]
[ 22 12 1 11 157]
[ 13 9 1 267 133]
[ 19 13 1 312 186]
[ 12 9 1 300 19]
[ 11 9 -2 334 139]
[ 14 10 -2 437 87]
[ 11 8 1 232 27]]
我的代碼是:
#--------------------
# Import Libraies
#====================
import numpy as np
import matplotlib.pyplot as plt
import os
import cv2
datasetPath = "/home/myPath"
#---------------------------------------------
# Extract faces, and Backgrounds from an image
#=============================================
def extData(imgPath, annots, foldPath, index):
'''
Function to Extract faces, and Backgrounds from an image.
Parameters:
@Param: imgPath : the specified image path(inside the DB).
@Param: annots : nd-array with shape m x 5, : m num of the detected faces in the image.
(5): max_radius | min_radius | angle | center_x | center_y
@Param: foldPath : the fold path where to save the extracted images.
@Param: index : a number to start naming the faces, backgrounds from it.
saves: m nd-array (m Faces), and m nd-array (m Background) in the foldPath
'''
fullImagePath = os.path.join(datasetPath, imgPath)
img = cv2.imread(fullImagePath)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# Create Faces
facesList = []
for row in range(annots.shape[0]):
# Initialize the Variables
xc = annots[row][3]
yc = annots[row][4]
Rmax = annots[row][0]
Rmin = annots[row][1]
theta = annots[row][2]
# Rectangle Borders
# represents the top left corner of rectangle
x0 = math.floor(xc - Rmin * math.sin(theta))
y0 = math.floor(yc - Rmax * math.sin(theta))
# represents the bottom right corner of rectangle
x1 = math.floor(xc + Rmin * math.sin(theta))
y1 = math.floor(yc + Rmax * math.sin(theta))
# Crop the face in rectangular window
face = img[y0:y1, x0:x1,:]
# store the coordinates of the face
facesList.append([x0, x1, y0, y1])
# make a directory to save the faces inside.
os.mkdir(os.path.join(foldPath,"/face/"))
cv2.imwrite(os.path.join(foldPath,"/face/", "face_{}".format(str(index+row)),face))
# Create Backgrounds
for row, face in enumerate(facesList):
# background = img[xb1:xb2,yb1:yb2,:]
# make a directory to save the backgrounds inside.
os.mkdir(os.path.join(foldPath,"/background/"))
# cv2.imwrite(os.path.join(foldPath,"/background/", "background_{}".format(str(index+row)),background))
#---------------------------------------------
您可以使用cv2.distanceTransform
計算與人臉的 L1 距離,並根據距離對矩形中心進行采樣,從而確保作物不會與“人臉”重疊:
import numpy as np
img = cv2.imread(fullImagePath)
# create a mask with zeros in "faces" and bonudary
mask = np.zeros(img.shape[:2], dtype=np.uint8)
mask[1:-1, 1:-1] = 1
for row in range(annots.shape[0]):
# Initialize the Variables
xc = annots[row][3]
yc = annots[row][4]
Rmax = annots[row][0]
Rmin = annots[row][1]
theta = annots[row][2]
# in case of rotation angles more than 45 degrees swap radius
if(theta > 45):
R = Rmax
Rmax = Rmin
Rmin = R
# Rectangle Borders
# represents the top left corner of rectangle
st = math.sin(theta)
st = st if st > 0 else -st
x0 = math.floor(xc - Rmin * st)
y0 = math.floor(yc - Rmax * st)
# represents the bottom right corner of rectangle
x1 = math.floor(xc + Rmin * st)
y1 = math.floor(yc + Rmax * st)
# Crop the face in rectangular window
mask[y0:y1, x0:x1] = 0
# once we have a map we can compute the distance of each non-face pixel to the nearest face
dst = cv2.distanceTransform(mask, cv2.DIST_L1, 3)
# pixels that are closer than 10 pixels (20//2) to a face, cannot be considered as good candidates. If you allow for IoU > 0 this can be relaxed a little.
dst[dst<10] = 0
# linear indices of pixels
idx = np.arange(np.prod(img.shape[:2]))
# sample centers
centers = np.random.choice(idx, size=annots.shape[0], replace=False, p=dst.flatten()/dst.sum())
# create the rectangles
windows = []
for i, c in enumerate(centers):
r = int(np.floor(dst.flat[c]))
r = np.random.choice(range(10,r)) # sample possible R from 10 to max possible
[y, x] = np.unravel_index(c, img.shape[:2])
windows.append((y-r, x-r, y+r, x+r))
結果窗口的示例如下所示:
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.