High Performance Visual Inspection Service Architecture - Squeezing the Most out of Commodity Servers

Abstract

The success of deep neural networks (DNN) in solving general machine vision problems has agitated a wave of its adoption in automated visual inspection solutions. Especially, DNN is able to learn by itself those relevant image features to reach a model that is robust to image quality variation, which promises very scalable solutions. The correlation between image acquisition hardware and image processing software, which is typical in traditional solutions, is alleviated. On this basis, we propose a novel visual inspection service architecture that is scalable, economic and reliable. The realization challenges of the visual inspection service are analyzed and the corresponding designs in model composition and model scheduling are presented. Special focus is placed on the runtime performance of inspection models and the efficient use of the computing resources of contemporary commodity servers.