模板匹配

dev_set_draw (‘margin‘)
read_image (Image, ‘D:/Project/PC/vision_2020/视库/样图/模板.jpg‘)
get_image_size (Image, Width, Height)

dev_get_window (WindowHandle)
*以下为创建mark（即ImageReduced）时用，且写到文件中
* draw_rectangle1 (WindowHandle, Row1, Column1, Row2, Column2)
* gen_rectangle1 (Rectangle, Row1, Column1, Row2, Column2)
* area_center (Rectangle, Area, RowRef, ColumnRef)
* reduce_domain (Image, Rectangle, ImageReduced)
* crop_domain (ImageReduced, ImagePart)
* write_image (ImagePart, ‘bmp‘, 0, ‘D://img.bmp‘)

*以下为直接读取mark文件
read_image (Image2, ‘D://img.bmp‘)

*求出mark的外框尺寸以及中心点
binary_threshold (Image2, Region, ‘max_separability‘, ‘dark‘, UsedThreshold)
area_center (Region, Area, RowRef, ColumnRef)
get_image_size (Image2, Width1, Height1)
gen_rectangle1 (Rectangle, 0, 0, Height1-1, Width1-1)

*建立查找模型
create_shape_model (Image2, ‘auto‘, rad(0), rad(365), ‘auto‘, ‘auto‘, ‘use_polarity‘, ‘auto‘, ‘auto‘, ModelID)

*打开文件并查找
read_image (Image1, ‘D:/Project/PC/vision_2020/视库/样图/模板_待测.jpg‘)
find_shape_model (Image1, ModelID, -0.39, 0.79, 0.5, 1, 0.5, ‘least_squares‘, 0, 0.9, Row, Column, Angle, Score)

*中心点打点
gen_cross_contour_xld (Cross, Row, Column, 16, Angle)

*仿射，形成搜索外框
vector_angle_to_rigid ( RowRef, ColumnRef, 0, Row, Column, Angle, HomMat2D1)
affine_trans_region (Rectangle, RegionAffineTrans, HomMat2D1, ‘nearest_neighbor‘)

*清除模型
clear_shape_model (ModelID)

模板匹配

原文：https://www.cnblogs.com/dingyd/p/12960598.html