1.基本概念
模板匹配: 在整个图像区域中发现与给定子图像匹配的小块区域
要素: ①模板图像T ②待检图像S
2.API 介绍
(1)模板匹配API
# 模板匹配 API
result = cv2.matchTemplate(image: Any, templ: Any, method: Any, result: Any = None, mask: Any = None)`
image: 待检图像S
templ: 模板图像T
method: 匹配方法
result: 二维矩阵,像素值代表匹配程度
cv2.TM_CCORR | 相关匹配 | 数值越大效果越好 |
cv2.TM_CCORR_NORMED | 归一化相关匹配 | 数值越大效果越好 |
cv2.TM_CCOEFF | 相关系数匹配 | 数值越大效果越好 |
cv2.TM_CCOEFF_NORMED | 相关系数匹配 | 数值越大效果越好 |
cv2.TM_SQDIFF | 平方差匹配 | 数值越小效果越好 |
cv2.TM_SQDIFF_NORMED | 平方差匹配 | 数值越小效果越好 |
(2)二维矩阵获取最大最小值及位置
# 在二维矩阵中获取最大最小值及最大最小值位置
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(src: Any, mask: Any = None)
min_val: 最小值
max_val: 最大值
min_loc: 最小值位置,如(2,5)
max_loc: 最大值位置,如(4,10)
(3)在图像上画出模板区域
# 在图像上画出矩形
cv2.rectangle(img: Any, pt1: Any, pt2: Any, color: Any, thickness: Any = None, lineType: Any = None, shift: Any = None)
img: 原图像
pt1: (x,y), 矩阵左上角的位置
pt2: (x+w, y+h), 矩阵右下角的位置
color: 例:(0,0,255)表示红色
thickness: 线条粗细
3.代码示例
import cv2
import numpy as np
source = cv2.imread('E:/PycharmProjects/source.jpg')
tpl = cv2.imread('E:/PycharmProjects/tpl.jpg')
def show(name, img):
cv2.imshow(name, img)
cv2.waitKey(0)
show('source', source)
show('template', tpl)
def template_demo():
methods = [cv2.TM_CCOEFF_NORMED, cv2.TM_CCORR_NORMED, cv2.TM_SQDIFF_NORMED]
th, tw = tpl.shape[:2]
for md in methods:
result = cv2.matchTemplate(source, tpl, md)
print(type(result))
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(result)
if md == cv2.TM_SQDIFF_NORMED:
tl = min_loc
else:
tl = max_loc
br = tl[0]+tw, tl[1]+th
cv2.rectangle(source, tl, br, (0, 0, 255), 3)
show('result'+np.str(md), result)
show('match'+np.str(md), source)
template_demo()
cv2.destroyAllWindows()
4.结果展示
原图:模板:
匹配后结果:
作出矩形框: