Cable surface defect real-time detection method and system based on machine vision

The invention discloses a cable surface defect real-time detection method and system based on machine vision, and the method comprises the steps: 1, constructing a cable defect detection network which comprises three parallel feature extraction branches, the input of the three feature extraction bra...

Full description

Saved in:
Bibliographic Details
Main Authors JIANG YUNYI, CHEN JUNFENG, DU JINGJING, LI QINGWU
Format Patent
LanguageChinese
English
Published 28.06.2022
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
Online AccessGet full text

Cover

More Information
Summary:The invention discloses a cable surface defect real-time detection method and system based on machine vision, and the method comprises the steps: 1, constructing a cable defect detection network which comprises three parallel feature extraction branches, the input of the three feature extraction branches is a cable surface image, and the output of the three feature extraction branches is a cable surface image; the output is the extracted image features; the outputs of the three feature extraction branches are cascaded according to different weights and then are sequentially input into three full-connection layers to obtain defect classification, and whether the cable surface image has defects is output; 2, training the cable defect detection network by adopting a training set; 3, adjusting and optimizing the trained cable defect detection network by adopting a test set; if the accuracy rate and the recall rate do not meet the preset requirements, training again; and 4, acquiring a cable surface image in real
Bibliography:Application Number: CN202210241575