还是车牌识别的例子
read_image (Image, 'C:/Users/LiZhiqiang/Desktop/车牌2.jpg')//读取图像 rgb1_to_gray (Image, GrayImage)//转化成灰度图像 threshold (GrayImage, Regions, 21, 163)//阈值选择 connection (Regions, ConnectedRegions)//断开区域 select_shape (ConnectedRegions, SelectedRegions1, 'area', 'and', 299.63, 1000)//特征选择，选中车牌 union1 (SelectedRegions1, RegionUnion)//把车牌合并成一个区域
如下图
shape_trans (RegionUnion, RegionTrans, 'convex')//将形状转换成矩形
orientation_region (RegionTrans, Phi)//得到区域的偏转角度 area_center (RegionTrans, Area, Row, Column)//计算区域面积和中心点坐标 vector_angle_to_rigid (Row, Column, Phi, Row, Column, 0, HomMat2D)//得到摆正图片的仿射矩阵 affine_trans_image (GrayImage, ImageAffineTrans, HomMat2D, 'constant', 'false')//仿射矩阵应用于图片
affine_trans_region (RegionTrans, RegionAffineTrans, HomMat2D, 'nearest_neighbor')//仿射矩阵应用于区域 reduce_domain (ImageAffineTrans, RegionAffineTrans, ImageReduced)//从图片中截取该矩形区域
后面的部分就跟上一节的车牌识别思路一样了
threshold (ImageReduced, Regions1, 0, 152)//设定阈值 connection (Regions1, ConnectedRegions1)//断开区域 sort_region (ConnectedRegions1, SortedRegions, 'character', 'true', 'row') read_ocr_class_mlp ('Document_0-9A-Z_NoRej.omc', OCRHandle) do_ocr_multi_class_mlp (SortedRegions, ImageReduced, OCRHandle, Class, Confidence)
