Computer vision in manufacturing: a bibliometric analysis and future research propositions

Computer vision for the past two decades has been used to simulate human capabilities and automate tasks, and in the process, has benefited all of us. Specifically, its application within the manufacturing context has garnered ample attention and interest from both academics and practitioners. Due to its large-scale applicability and adoption potential, extensive research has been conducted to understand and appreciate it is working. However, extant research in this domain is rather disjointed, thereby delimiting the otherwise vast scope and knowledge boundaries. Thus, this study utilizes bibliometric analysis to synthesize extant literature within this field to address this lacuna. We analyzed 897 articles from Scopus, entailing contributions from 309 journals, 108 countries, 2138 authors, and 1334 organizations from 1981 to 2022. Additionally, we analyzed citation and co-authorship networks to acknowledge prominent authors, organizations, and countries within this domain. The thematic classification of extant literature through bibliographic coupling identified five major thematic areas: automated visual inspection, object tracking and process controlling, real-time monitoring, roughness inspection, and profile projection. Importantly, we used both knowledge and insights from our findings, and propose scope for future research.

Automated summary

Computer vision has been widely applied in the manufacturing context to automate tasks and simulate human capabilities. However, existing research in this field is fragmented, and there is a need for more comprehensive studies to fill this gap. This study uses bibliometric analysis to synthesize extant literature and provide insights for future research.