An Image Processing Pipeline for Automated Packaging Structure Recognition

TL;DR

This paper presents a computer vision-based system for fully automated recognition of packaging structures in logistics using RGB images, aiming to reduce manual effort in supply chain verification processes.

Contribution

It introduces a novel system design for packaging recognition and evaluates its performance on real-world logistics data, discussing key algorithmic decisions.

Findings

High accuracy in packaging structure recognition

Effective system performance on real-world data

Potential to automate logistics verification processes

Abstract

Dispatching and receiving logistics goods, as well as transportation itself, involve a high amount of manual efforts. The transported goods, including their packaging and labeling, need to be double-checked, verified or recognized at many supply chain network points. These processes hold automation potentials, which we aim to exploit using computer vision techniques. More precisely, we propose a cognitive system for the fully automated recognition of packaging structures for standardized logistics shipments based on single RGB images. Our contribution contains descriptions of a suitable system design and its evaluation on relevant real-world data. Further, we discuss our algorithmic choices.