abstract |
The invention discloses a part detection method based on machine vision, which adopts a weighted hybrid deep learning target identification algorithm, and has a secondary detection method. The meta deep learning algorithms of the weighted hybrid deep learning target identification algorithm include the RCNN algorithm, the Faster-RCNN algorithm, the R-FCN algorithm, the YOLO algorithm, the SSD algorithm and the DenseBox algorithm; check the position of the rectangular area corresponding to the defects marked by each meta deep learning algorithm , to judge whether they are adjacent or overlapping; merge adjacent or overlapping rectangular areas. Through the multi-algorithm fusion processing method, the same image object is identified and processed, and the same mark that can be compared with each other is used, and then the identification result with the most defect possibility identified by the multi-algorithm is taken. the accuracy of image recognition. |