视觉应用——印刷质量检测

合集 - 视觉应用(7)

1.光度立体法检测----手机按键效果图2024-02-292.引导定位——坐标计算2024-02-293.不同光源波段长度2024-02-29

4.视觉应用——印刷质量检测2024-03-14

5.ccBoard::HardwareNotlnitialized: Performance driver not installed2024-04-116.棋盘格生成2024-05-097.常用镜头接口2024-05-13

收起

*此示例演示了使用变体模型的打印检查。
*变异模型使用单个模型图像进行训练。在应用打印检测之前，图像将缩放到与模型相同的灰度值范围。
dev_update_off ()
dev_close_window ()
* 
* Read model image and init visualization
*读取模型图像并初始化可视化
read_image (ModelImage, 'cap_illumination/cap_illumination_01')
get_image_size (ModelImage, Width, Height)
dev_open_window (0, 0, Width / 2, Height / 2, 'black', WindowHandle)
set_display_font (WindowHandle, 14, 'mono', 'true', 'false')
* 
* Segment model region
*分割模型区域
dev_display (ModelImage)
get_model_region (ModelImage, RegionROI, ImageReduced)
area_center (RegionROI, Area, RowModel, ColumnModel)
dev_set_draw ('margin')
dev_set_color ('green')
dev_display (RegionROI)
* 
* Create model for shape-based-matching
*创建模型
disp_message (WindowHandle, 'Model generation...', 'window', 12, 12, 'black', 'true')
create_scaled_shape_model (ImageReduced, 'auto', 0, rad(360), 'auto', 0.8, 1.2, 'auto', 'auto', 'use_polarity', 'auto', 'auto', ModelID)
get_shape_model_contours (ModelContours, ModelID, 1)
* Transform model contours from the original position for visualization
*从原始位置变换模型轮廓以进行可视化
hom_mat2d_identity (HomMat2DIdentity)
hom_mat2d_translate (HomMat2DIdentity, RowModel, ColumnModel, HomMat2DTranslate)
affine_trans_contour_xld (ModelContours, ModelContoursAffineTrans, HomMat2DTranslate)
* 
* Create variation model for print inspection
*创建用于打印检测的变异模型
create_variation_model (Width, Height, 'byte', 'direct', VariationID)
* Generate variation image
sobel_amp (ModelImage, VarImage, 'sum_abs', 5)
prepare_direct_variation_model (ModelImage, VarImage, VariationID, [20,25], [1.6,1.6])
* 
* Get gray value range of the variation model
*获取变异模型的灰度值范围
get_grayval_range (ModelImage, RegionROI, RegionForeground, RegionBackground, BackgroundGVModel, ForegroundGVModel)
* 
* Perform print inspection
*执行印刷检测
for I := 1 to 9 by 1
    read_image (rImage, 'cap_illumination/cap_illumination_' + I$'.2')
    inspect_cap (rImage, RegionROI, WindowHandle, ModelID, VariationID, RowModel, ColumnModel, BackgroundGVModel, ForegroundGVModel)
    if (I < 9)
        disp_continue_message (WindowHandle, 'black', 'true')
        stop ()
    endif
endfor
* 
clear_shape_model (ModelID)
clear_variation_model (VariationID)