Halcon车牌识别案例

1、shape_trans :形状转化  ，（1）'convex'：连通所有像素     （2）'rectangle1'：最小外接矩形2、字符识别

3、fill_up :孔洞填充

4、二值化
5、RGB到其他颜色空间互转
6、reduce_domain 选择图像中的指定区域大小显示图像

* Image Acquisition 01: Code generated by Image Acquisition 01
read_image (Image, 'C:/Users/Administrator/Desktop/aa.PNG')
*分解RGB通道
decompose3 (Image, Image1, Image2, Image3)
*转换RGB图像空间到另一种图像空间 hsv:色度、亮度、饱和度
trans_from_rgb (Image1, Image2, Image3, ImageResult1, ImageResult2, ImageResult3, 'hsv')
*二值化 0或255
threshold (ImageResult3, Regions, 71, 109)
connection (Regions,ConnectedRegions)
select_shape (ConnectedRegions, SelectedRegions, 'area', 'and', 1697.59, 3330.24)
*填充孔洞
fill_up (SelectedRegions, RegionFillUp)
opening_circle (RegionFillUp, RegionOpening,3)
connection (RegionOpening, ConnectedRegions1)
select_shape (ConnectedRegions1, SelectedRegions1, 'area', 'and', 3224.77, 4463.3)
*改变