基于机器视觉的坯布疵点实时自动检测平台
The Machine Vision-Based Platform for Real-Time Grey Fabric Defect Detection
李冠志 1万贤福 2汪军 3李立轻 2陈霞2
作者信息
- 1. 东华大学纺织面料技术教育部重点实验室,上海201620
- 2. 东华大学纺织学院,上海201620
- 3. 东华大学纺织面料技术教育部重点实验室,上海201620;东华大学纺织学院,上海201620
- 折叠
摘要
为了克服人工检测坯布疵点过程中存在的低效率、高误检率、高漏检率等问题,设计并实现了一款能兼顾实时性和准确性要求的坯布自动检测平台.该平台包括织物传动系统、光源和成像系统、图像采集与处理系统、人机交互系统4个组成部分.在详细阐述了图像采集与处理系统的设计之后,结合AR谱算法对坯布自动检测平台进行了相关调试和试验验证,结果表明该平台已实现了预期的研发要求.
Abstract
To overcome the drawbacks of fabric inspection performed by human inspectors,such as low efficiency,high false detection and high missing detection rate,an automated fabric inspection platform that can meet real-time and accurate requirements is designed and implemented.This platform is consisted of four parts:fabric drive system,illumination & imaging system,image acquisition & processing system and human-computer interaction system.After elaborating the design of image acquisition & processing system,a validation experiment is conducted to confirm the usefulness of the proposed platform with the AR spectral analysis algorithm,achieving the expected requirements.
关键词
机器视觉/自动验布/疵点检测/数字信号处理(DSP)/现场可编程门阵列(FPGA)Key words
machine vision/automatic fabric inspecting/defect detection/digital signal processing(DSP)/field-programmable gate array(FPGA)引用本文复制引用
基金项目
国家自然科学基金资助项目(61271006,61379011)
中央高校基本科研业务费专项资金资助项目()
出版年
2014
NETL
NSTL
维普
万方数据