Cigarette primary processing procedure material blockage identification system and method based on deep learning

• Main Authors: CHEN HUIPIN, ZHOU YEZHOU, LI MINCHENG, XU QIANG, LEI YANG, LIU WEIBIN, GAO JINZHOU, ZHANG ZHENKAI, QIN CHUANYANG, LI JUNSHEN
• Format: Patent
• Language: Chinese; English
• Published: 28.07.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses a cigarette primary processing process blockage identification system based on deep learning, and the system is characterized in that the system comprises an image collection module which is used for collecting a real-time three-dimensional image and a historical three-dimensional image from a blockage point at high frequency; the image processing module is used for carrying out preprocessing, feature extraction and marking on the collected image data; the deep learning model modeling module is used for carrying out deep learning by using historical image data obtained by image processing and the material blocking area mask, and establishing an identification model; the model evaluation module is used for evaluating, feeding back and adjusting the model; the model operation module is used for performing model operation on the identification model and the real-time image data subjected to image processing; and the material blocking identification analysis application module is used for