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

作　　者：李冠志 万贤福[2] 汪军[1,2] 李立轻[2] 陈霞[2] 

机构地区：[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

出　　处：《东华大学学报（自然科学版）》2014年第1期11-16,共6页Journal of Donghua University(Natural Science)

基　　金：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

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.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) digital SIGNAL processing(DSP) field-programmable GATE array(FPGA) 

分 类 号：TS101.9[轻工技术与工程—纺织工程] TP274.4[轻工技术与工程—纺织科学与工程]