An Industrial-Strength Pipeline for Recognizing Fasteners

Abstract

Image classification and computer vision for search are rapidly emerging in today's technology and consumer markets. Specifically, startup companies have leveraged state-of-the-art image search capabilities in automating recognition of logos and titles, pop-up advertisements based on video content, and recommendations of products in the fashion industry. Partpic focuses on image search for replacement parts, and we present our industrial pipeline for such, with application to fasteners. We discuss how we have aimed to overcome issues such as acquiring enough training data, training and classification of many different types of fasteners, identification of customized specifications of fasteners (such as finish type, dimensions, etc.), establishing constraints for the user to take an good-enough image, and scalability of many pieces of data associated with thousands of fasteners.