對于常規(guī)的pcb的元件缺失檢測大致步驟。
第一：售前，需要快速判斷元件是貼片，引腳式，常規(guī)裸露式，并使用ROI直接進(jìn)行快速的blob分析，使用特征面積選擇即可快速的完成早期評估工作。
第二：根據(jù)需求判斷，是否需要模板匹配單對多還是多對多的處理。
第三：實際代碼書寫，對于模板匹配的輸出文件，應(yīng)以寫入新的文件。
本次需求：對c6旁邊的電阻進(jìn)行檢測是否存在電阻或者電阻脫落的情況
halcon程序

read_image (Image, 'D:/shijue/11/pcb缺陷/Image__2022-05-04__17-01-48.bmp') *讀圖 gen_rectangle2 (ROI_0, 58.5102, 543.681, rad(-101.309), 70.7985, 80.6545) *對c6進(jìn)行ROI選取 reduce_domain (Image, ROI_0, ImageReduced2) *裁圖 rgb1_to_gray (ImageReduced2, GrayImage) *轉(zhuǎn)為單通道灰度值 threshold (GrayImage, Regions2, 168, 220) *二值化扣出c6 closing_rectangle1 (Regions2, RegionClosing2, 5,5) *膨脹，防止字符沒有扣好 reduce_domain (Image, RegionClosing2, ImageReduced3) *裁圖 inspect_shape_model (ImageReduced3, ModelImages, ModelRegions,5,25) select_obj (ModelImages, ObjectSelected, 1) dev_display (ObjectSelected) create_shape_model (ImageReduced3, 3, 0, rad(360), 'auto', 'none', 'use_polarity', 30, 10, ModelID) get_shape_model_contours (ModelContours, ModelID, 1) *以上創(chuàng)建模板 find_shape_model (Image, ModelID, 0, rad(360), 0.7, 1, 0.5, 'least_squares', 0, 0.5, RowCheck, ColumnCheck, AngleCheck, Score) *根據(jù)模板尋找c6 if (|Score| > 0)*判斷是否找到c6vector_angle_to_rigid (0, 0, 0, RowCheck, ColumnCheck, AngleCheck, HomMat2D)affine_trans_region (ObjectSelected, RegionAffineTrans, HomMat2D, 'nearest_neighbor')affine_trans_image (ModelImages, ImageAffineTrans, HomMat2D, 'constant', 'false')dev_display (ImageAffineTrans)dev_display (RegionAffineTrans)*對找到的c6進(jìn)行仿射變化orientation_region (RegionAffineTrans, Phi)area_center (RegionAffineTrans, Area, Row, Column)*獲取c6的坐標(biāo)和角度vector_angle_to_rigid (Row, Column, 0, Row, Column, rad(0), HomMat2D)affine_trans_image (Image, ImageAffineTrans, HomMat2D, 'constant', 'false')affine_trans_region (RegionAffineTrans, RegionAffineTrans2, HomMat2D, 'nearest_neighbor')*將c6運用到圖中reduce_domain (ImageAffineTrans, RegionAffineTrans2, ImageReduced4)*裁圖rgb1_to_gray (ImageReduced4, GrayImage1)*轉(zhuǎn)為單通道灰度shape_trans (GrayImage1, RegionTrans, 'convex')*練成一個區(qū)域area_center (RegionTrans, Area1, Row1, Column1)orientation_region (RegionTrans, Phi1)*獲取中心坐標(biāo)和角度gen_rectangle2_contour_xld (Rectangle1, Row, Column1-300, Phi1, 150,80)*根據(jù)實際繪制一個在c6旁的元件的矩形輪廓dev_display (ImageAffineTrans)dev_display (Rectangle1)*顯示檢測是否正確gen_rectangle2 (Rectangle1, Row, Column1-300, Phi1, 150,80)*根據(jù)輪廓，繪制矩形區(qū)域reduce_domain (ImageAffineTrans, Rectangle1, ImageReduced5)*裁圖，對元件進(jìn)行處理decompose3 (ImageReduced5, Red, Green, Blue)trans_from_rgb (Red, Green, Blue, Hue, Saturation, Intensity, 'hsv')*轉(zhuǎn)化為hsvthreshold (Saturation, Regions, 0, 89)*對s進(jìn)行二值化opening_rectangle1 (Regions, RegionOpening, 3,3)closing_rectangle1 (RegionOpening, RegionClosing1, 3,3)*以上為blob分析connection (RegionClosing1, ConnectedRegions1)select_shape (ConnectedRegions1, SelectedRegions1, 'area', 'and', 11907.4, 14351.9)*判斷SelectedRegions1數(shù)組是否為空即可 endif *以下為快速實驗處理，可在售前階段，快速評估產(chǎn)品是否有能力完成 *沒有元件處理，常規(guī)blob分析 gen_rectangle2 (ROI_0, 157, 780.727, rad(-12.3391), 151.872, 74.1818) reduce_domain (Image, ROI_0, ImageReduced) decompose3 (ImageReduced, Red, Green, Blue) trans_from_rgb (Red, Green, Blue, Hue, Saturation, Intensity, 'hsv') threshold (Saturation, Regions, 0, 89) opening_rectangle1 (Regions, RegionOpening, 3,3) closing_rectangle1 (RegionOpening, RegionClosing1, 3,3) connection (RegionClosing1, ConnectedRegions1) select_shape (ConnectedRegions1, SelectedRegions1, 'area', 'and', 11907.4, 14351.9)*有元件處理 read_image (Image1, 'D:/shijue/11/pcb缺陷/Image__2022-04-03__17-25-28.bmp') gen_rectangle2 (ROI_0, 866.364, 915.182, rad(17.1027), 126.123, 79.6594) reduce_domain (Image1, ROI_0, ImageReduced1) decompose3 (ImageReduced1, Red1, Green1, Blue1) trans_from_rgb (Red1, Green1, Blue1, Hue1, Saturation1, Intensity1, 'hsv') threshold (Saturation1, Regions1, 0, 81) opening_rectangle1 (Regions1, RegionOpening1, 3,3) closing_rectangle1 (RegionOpening1, RegionClosing,3,3) connection (RegionClosing, ConnectedRegions) select_shape (ConnectedRegions, SelectedRegions, 'area', 'and', 11907.4, 14351.9) *判斷SelectedRegions數(shù)組不為為空即可

實際完成效果

無原件輸出面積選擇為空

測試的圖片參考
由于csdn有要求的圖片上傳大小，所以這里使用jpg壓縮圖像并不是原圖，有需要原圖的可以私信我。

總結(jié)

以上是生活随笔為你收集整理的基于视觉halcon的对pcb元件缺失快速检测参考处理的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。