摘要
In yarn evenness inspection based on image processing,due to serious noise,morphological method can not separate yarn from the blackboard entirely.In order to solve this problem,this paper proposes a denosing method that combines morphology with the image decomposition based on partial differential equation(PDE).Before denosing automatical skew detection is introduced to avoid the calculation error caused by image tilting.The experimental results show that the hairiness can be removed completely,and the characteristics of yarn can be reserved.The inspection result is well coincided with visual assessment.
In yarn evenness inspection based on image processing,due to serious noise,morphological method can not separate yarn from the blackboard entirely.In order to solve this problem,this paper proposes a denosing method that combines morphology with the image decomposition based on partial differential equation（PDE）.Before denosing automatical skew detection is introduced to avoid the calculation error caused by image tilting.The experimental results show that the hairiness can be removed completely,and the characteristics of yarn can be reserved.The inspection result is well coincided with visual assessment.
出处
《辽宁师范大学学报（自然科学版）》
CAS
北大核心
2008年第4期404-406,共3页
Journal of Liaoning Normal University:Natural Science Edition
关键词
纱
纺织技术
形态学法
纺织机
yarn evenness
automatic skew detection
mathematical morphology
partial differential equation
