A novel vision-based mold monitoring system in an environment of intense vibration. (19th September 2017)

• Record Type: Journal Article
• Authors: Hu, Fen; He, Zaixing; Zhao, Xinyue; Zhang, Shuyou
• Is Part Of: Measurement science & technology. Volume 28:Number 10(2017:Oct.)
• Publication Date: 2017-09-19
• Subjects: mold monitoring -- machine vision -- image matching -- SIFT -- global feature; Physical measurements -- Periodicals; Scientific apparatus and instruments -- Periodicals; Equipment and Supplies -- Periodicals; Science -- instrumentation -- Periodicals; Technology -- instrumentation -- Periodicals; Mesures physiques -- Périodiques; Physical measurements; Scientific apparatus and instruments; Periodicals; 502.87
• DOI: 10.1088/1361-6501/aa8537
• Languages: English
• ISSNs: 0957-0233

Abstract

Abstract: Mold monitoring has been more and more widely used in the modern manufacturing industry, especially when based on machine vision, but these systems cannot meet the detection speed and accuracy requirements for mold monitoring because they must operate in environments that exhibit intense vibration during production. To ensure that the system runs accurately and efficiently, we propose a new descriptor that combines the geometric relationship-based global context feature and the local scale-invariant feature transform for the image registration step of the mold monitoring system. The experimental results of four types of molds showed that the detection accuracy of the mold monitoring system is improved in the environment with intense vibration.