需求:
比如给你下面这张图片,测出下面这个黑色块的尺寸大小,并返回黑色块在图像中像素位置的对应坐标
代码里面的width是随便给的,就像素与实际大小对应的比例尺寸,可调
代码及注释
from scipy.spatial import distance as dist
from imutils import perspective
from imutils import contours
import numpy as np
import imutils
import cv2
# 中点计算
def midpoint(ptA, ptB):
return (ptA[0] + ptB[0]) * 0.5, (ptA[1] + ptB[1]) * 0.5
width = 5
# 加载图像,将其转换为灰度
image = cv2.imread('111.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# 高斯平滑,使图像稍微模糊
gray = cv2.GaussianBlur(gray, (7, 7), 0)
# 执行边缘检测,然后执行扩张+侵蚀 闭合对象边之间的间隙(形态学运算移除斑点, 膨胀腐蚀操作)
edged = cv2.Canny(gray, 78, 134)
edged = cv2.dilate(edged, None, iterations=1)
edged = cv2.erode(edged, None, iterations=1)
# 在边缘图中查找轮廓
cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
# 从左到右对轮廓进行排序,并初始化“每公制像素”校准变量
(cnts, _) = contours.sort_contours(cnts)
pixelsPerMetric = None
# 对检测到的所有轮廓进行循环
for c in cnts:
# 如果轮廓不够大,忽略它,2000是阈值
if cv2.contourArea(c) < 2000:
continue
""" 计算轮廓的旋转边界框"""
orig = image.copy()
# 获取最小外接矩阵,中心点坐标,宽高,旋转角度
box = cv2.minAreaRect(c)
# 获取矩形四个顶点,浮点型
box = cv2.cv.BoxPoints(box) if imutils.is_cv2() else cv2.boxPoints(box)
# 数值取整
box = np.array(box, dtype="int")
print(box)
# 对轮廓中的点进行排序,使它们以左上、右上、右下和左下的顺序出现,然后绘制旋转边界框的轮廓
box = perspective.order_points(box)
cv2.drawContours(orig, [box.astype("int")], -1, (0, 255, 0), 2)
# 为符合条件的轮廓绘框
for (x, y) in box:
cv2.circle(orig, (int(x), int(y)), 5, (0, 0, 255), -1)
# 打开有序的边界框,然后计算左上和右上坐标之间的中点,然后是左下和右下坐标之间的中间点
(tl, tr, br, bl) = box
(tltrX, tltrY) = midpoint(tl, tr)
(blbrX, blbrY) = midpoint(bl, br)
# 计算左上角点和右上角点之间的中点,然后计算右上角和右下角的中点
(tlblX, tlblY) = midpoint(tl, bl)
(trbrX, trbrY) = midpoint(tr, br)
# 绘制蓝色中间点
cv2.circle(orig, (int(tltrX), int(tltrY)), 5, (255, 0, 0), -1)
cv2.circle(orig, (int(blbrX), int(blbrY)), 5, (255, 0, 0), -1)
cv2.circle(orig, (int(tlblX), int(tlblY)), 5, (255, 0, 0), -1)
cv2.circle(orig, (int(trbrX), int(trbrY)), 5, (255, 0, 0), -1)
# 在中点之间绘制线,然后将中间点与紫色线连接
cv2.line(orig, (int(tltrX), int(tltrY)), (int(blbrX), int(blbrY)),
(255, 0, 255), 2)
cv2.line(orig, (int(tlblX), int(tlblY)), (int(trbrX), int(trbrY)),
(255, 0, 255), 2)
# 计算中点之间的欧几里得距离
dA = dist.euclidean((tltrX, tltrY), (blbrX, blbrY))
dB = dist.euclidean((tlblX, tlblY), (trbrX, trbrY))
# 如果每个度量的像素尚未初始化,则将其计算为像素与提供的度量的比率(在本例中为英寸)
if pixelsPerMetric is None:
pixelsPerMetric = dB / width
# 计算尺寸的大小
dimA = dA / pixelsPerMetric
dimB = dB / pixelsPerMetric
print(dimA)
print(dimB)
# 在图像上绘制尺寸大小
cv2.putText(orig, "{:.1f}cm".format(dimA),
(int(tltrX - 15), int(tltrY - 10)), cv2.FONT_HERSHEY_SIMPLEX,
0.65, (255, 255, 255), 2)
cv2.putText(orig, "{:.1f}cm".format(dimB),
(int(trbrX + 10), int(trbrY)), cv2.FONT_HERSHEY_SIMPLEX,
0.65, (255, 255, 255), 2)
# 显示输出图像
cv2.imshow("Image", orig)
cv2.waitKey(0)