一、HALCON学习笔记（容器液位缺陷检测）

* In this example a fill level check for the
* pharmaceutical industry is demonstrated. The task is
* to check for the fill level of each single nose drop ampoule.
* To do so, we first locate each ampoule head by applying
* shape-based matching, then we find the fill level
* by measuring the gray level change using a 1D Measuring.
*
* 1 绘图设置
dev_close_window ()
dev_update_off ()
read_image (Image, 'ampoules/ampoules_01')
get_image_size (Image, Width, Height)
dev_open_window_fit_image (Image, 0, 0, -1, -1, WindowHandle)
dev_set_line_width (2)
dev_set_draw ('margin')
set_display_font (WindowHandle, 16, 'mono', 'true', 'false')
*
* Create a model for the ampoule head to align the measure handle
* 2 创建形状模板
gen_rectangle1 (Rectangle, 230, 280, 317, 330)
reduce_domain (Image, Rectangle, ImageModel)
create_shape_model (ImageModel, 'auto', 0, 0, 'auto', 'auto', 'use_polarity', 'auto', 'auto', ModelID)
*
* Initialize the measure handle
* 3 初始化测量句柄 准备提取垂直于矩形的直线边。
gen_measure_rectangle2 (0, 0, rad(90), 75, 20, Width, Height, 'bilinear', MeasureHandle)
Tolerance := 15
*
* Determine the fill level
* 4 确定填充水平
NumImages := 8
for Index := 1 to NumImages by 1read_image (Image, 'ampoules/ampoules_' + Index$'.2d')ColumnEdges := []FillLevelHeight := []* 5 模板匹配，找到瓶口行坐标find_shape_model (Image, ModelID, 0, 0, 0.7, 0, 0.1, 'least_squares', 0, 0.9, Row, Column, Angle, Score)* 6 求匹配到的平均行坐标MeanRow := mean(Row)* 液位范围矩形参考行坐标RefLevel := MeanRow - 160* Display tolerance areadev_display (Image)dev_set_line_width (1)dev_set_color ('white')* 7 绘制正常液位参考矩形gen_rectangle2 (AcceptLevel, RefLevel, mean(Column), 0, 30 + (max(Column) - min(Column)) / 2, Tolerance)dev_display (AcceptLevel)dev_set_line_width (2)* *  Determine fill level of each ampouleErrors := 0for Idx := 0 to |Score| - 1 by 1* 8 准备提取垂直于矩形的直线边 -> 转换一个度量对象translate_measure (MeasureHandle, MeanRow - 135, Column[Idx])* Search for the topmost edge* 9 提取垂直于矩形或环形圆弧的直线边缘measure_pos (Image, MeasureHandle, 2, 7, 'all', 'first', RowEdge, ColumnEdge, Amplitude, Distance)* 10 保存单个容器液位坐标FillLevelHeight := [FillLevelHeight,RowEdge]ColumnEdges := [ColumnEdges,ColumnEdge]* 11 为每个输入点(液位)生成一个十字形的XLD轮廓线gen_cross_contour_xld (Cross, RowEdge, ColumnEdge, 15, 0)gen_rectangle2 (FillLevel, RowEdge, ColumnEdge, 0, 28, 20)* 12 判断液位是否在容忍限度内if (abs(FillLevelHeight[Idx] - RefLevel) >= Tolerance)gen_rectangle2 (Cross, MeanRow - 133, Column[Idx], 0, 35, 90)gen_cross_contour_xld (Cross, FillLevelHeight[Idx], ColumnEdges[Idx], 15, 0)gen_rectangle2 (FillLevel, FillLevelHeight[Idx], ColumnEdges[Idx], 0, 28, 20)Errors := Errors + 1dev_set_color ('red')dev_display (Cross)disp_message (WindowHandle, 'NG', 'image', FillLevelHeight[Idx] - 50, ColumnEdges[Idx] - 10, 'red', 'false')elsedisp_message (WindowHandle, 'OK', 'image', FillLevelHeight[Idx] - 50, ColumnEdges[Idx] - 10, 'green', 'false')dev_set_color ('green')endifdev_display (FillLevel)dev_display (Cross)endfor* * Check, whether the fill level is within the allowed range - does not deviate too much* from average fill level* * Display statisticsif (Errors > 0)disp_message (WindowHandle, Errors + ' BAD', 'window', 10, 12, 'red', 'true')elsedisp_message (WindowHandle, 'All OK', 'window', 10, 12, 'forest green', 'true')endifif (Index < NumImages)disp_continue_message (WindowHandle, 'black', 'true')stop ()endif
endfor
*
close_measure (MeasureHandle)
clear_shape_model (ModelID)

该例程中重要的三个函数为
- 3 初始化测量句柄准备提取垂直于矩形的直线边。
  gen_measure_rectangle2 (0, 0, rad(90), 75, 20, Width, Height, 'bilinear', MeasureHandle)
- 8 准备提取垂直于矩形的直线边 -> 转换一个度量对象
  translate_measure (MeasureHandle, MeanRow - 135, Column[Idx])
- 9 提取垂直于矩形或环形圆弧的直线边缘
  measure_pos (Image, MeasureHandle, 2, 7, 'all', 'first', RowEdge, ColumnEdge, Amplitude, Distance)
以上三个函数相互配合实现对图像区域内垂直于矩形的直线边的捕获，从而获得液位，最终与可容忍液位相匹配，判断是否越界，完成缺陷检测。

一、HALCON学习笔记（容器液位缺陷检测）相关推荐

Halcon 学习笔记八：颜色识别
Halcon 学习笔记八:颜色识别一.图像处理需要的知识二.图像处理的预处理和分割过程二.颜色识别的方法三.例子一四.例子二五.例子三一.图像处理需要的知识 1.图像处理基础(rgb(h ...
Halcon学习笔记：划痕、油污、瑕疵
Halcon学习笔记:划痕.油污.瑕疵划痕.油污.瑕疵,常用的方法有傅里叶变换和Blob分析. 1.表面划痕 invert_image(Image,ImageInvert1) mult_image ...
Halcon 学习笔记五：几何定位+仿射变换+测量
Halcon 学习笔记五:几何定位+仿射变换+测量定位流程例子一例子二(药片的定位) 例子三(充电宝定位) 例子四(车牌定位) 其他定位流程 blob分析模板匹配 (仿射变换成标准的形状) ...
OpenCV for Ios 学习笔记(4)－标记检测1
本文原始地址:OpenCV for Ios 学习笔记(4)-标记检测1 简单的标记经常是以白色块和黑色块构成的规则图形.因为我们预先知道这些因素,所以我们可以很容易检测标记. 如图: 首先,我们需要找 ...
Halcon学习笔记（三）---数据类型
Halcon学习笔记(三)---数据类型 halcon只能在单独行进行注释,不能在语句后面进行注释. 1.tuple(元组,重数) 赋值符号":=" tuple算子: (1)变量定 ...
Halcon学习笔记：select_points_object_model_3d（3D对象模型阀值分割）
Halcon学习笔记:select_points_object_model_3d 3D对象模型阀值分割 This example program shows how to use the operat ...
Halcon学习笔记：xyz_attrib_to_object_model_3d示例
Halcon学习笔记:xyz_attrib_to_object_model_3d--从X.Y和Z图像中创建3D对象模型同时附加属性 xyz_attrib_to_object_model_3d.hdev ...
Halcon学习笔记：1D Measuring一维测量_fuse.hdev灯丝测量示例
Halcon学习笔记:1D Measuring一维测量_fuse.hdev灯丝测量示例一.基本概念基本流程为: 获取图像对图像进行灰度值标定 (针对相机获取的图像灰度和输入能量之间的非线性关系, ...
Halcon学习笔记(一)：Qt+Halcon联合开发配置
Halcon学习笔记(1):Qt+Halcon联合开发配置首先是新建一个QT项目qtest_hc 方法一: 1)QT项目文件 qtest_hc 添加库: #1.包含目录添加 INCLUDEPATH ...

一、HALCON学习笔记（容器液位缺陷检测）

一、HALCON学习笔记（容器液位缺陷检测）

一、HALCON学习笔记（容器液位缺陷检测）相关推荐

最新文章

热门文章