Developing the Wheel Image Similarity Application with Deep Metric Learning: Hyundai Motor Company Case

The global automobile market experiences quick changes in design preferences. In response to the demand shifts, manufacturers now try apply new technologies bring a novel faster. this paper, we introduce application that performs similarity verification task of wheel designs using an AI model and cloud computing technology. At Jan 2022, successfully implemented process Hyundai Motor Company’s team shortened time by 90% maximum 10 minutes. We believe study is first build image database empirically prove cross-entropy loss does similar tasks as pairwise losses do embedding space. As result, automated Motor’s similarity. With few clicks, end-users could take advantage our application.