from imutils import paths
import numpy as np
import imutils
import cv2
images = 'C:\learn\python\images\scottsdale' # 输入图片文件夹路径
output = 'C:\learn\python\output.png' # 输出图片名称
crop = True
imagePaths = sorted(list(paths.list_images(images)))
images = []
# 读取文件夹图片
for imagePath in imagePaths:
image = cv2.imread(imagePath)
images.append(image)
# 创建缝合器
stitcher = cv2.Stitcher_create()
(status, stitched) = stitcher.stitch(images)
# status:状态,0代表成功
if status == 0:
# 裁剪图像
if crop:
# 在拼图周围添加2像素
stitched = cv2.copyMakeBorder(stitched, 2, 2, 2, cv2.BORDER_CONSTANT, (0, 0, 0))
# 对图像进行灰度化和阈值化
gray = cv2.cvtColor(stitched, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY)[1]
# 查找阈值图像的轮廓
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
c = max(cnts, key=cv2.contourArea)
# 在这个轮廓下绘制最大的矩形
mask = np.zeros(thresh.shape, dtype="uint8")
(x, y, w, h) = cv2.boundingRect(c)
cv2.rectangle(mask, (x, y), (x + w, y + h), 255, -1)
# 创建两个遮罩
# minRect作为不断腐蚀的矩形
# sub作为阈值图像和minRect的插值来进行判断
minRect = mask.copy()
sub = mask.copy()
while cv2.countNonZero(sub) > 0:
minRect = cv2.erode(minRect, None)
sub = cv2.subtract(minRect, thresh)
# 得到最小的矩形,提取其范围坐标
cnts = cv2.findContours(minRect.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
c = max(cnts, key=cv2.contourArea)
(x, y, w, h) = cv2.boundingRect(c)
# 使用该范围坐标对原图进行裁剪
stitched = stitched[y:y + h, x:x + w]
# 保存图片
cv2.imwrite(output, stitched)
else:
print("拼接失败,错误码:{}".format(status))
