Method and device for detecting defects of cigarette blast beads

• Main Authors: TAMIZU, WANG NING, LIU MING
• Format: Patent
• Language: Chinese; English
• Published: 26.04.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses a defect detection method and device for cigarette blast beads, and relates to the field of cigarette production, and the method comprises the following steps: S1, constructing a defect detection model; s2, acquiring a training data set, and training and optimizing the defect detection model to obtain an optimized defect detection model; s3, acquiring a finished product image of the to-be-detected cigarette blast bead in real time; s4, filtering the finished image to obtain a first image; s5, positioning the position of a blasting bead in the first image, and segmenting the first image to obtain a blasting bead image; s6, inputting the blasting bead image into the optimized defect detection model to obtain a defect detection result of the blasting bead image; by utilizing the neural network technology, various defects in the blast beads can be automatically and efficiently detected, the problems of errors and fatigue caused by manual detection are avoided, the detection precision is im