Michael Schadler
Research Assistant
Institute of Logistics Engineering - Graz University of Technology
Dominik Stadlthanner
Research Assistant
Institute of Logistics Engineering - Graz University of Technology
Michael Schedler
Research Assistant
Institute of Logistics Engineering - Graz University of Technology
Bastian Mayer
Student
Bastian Mayer
Institute of Logistics Engineering - Graz University of Technology
Associate Professor
Institute of Logistics Engineering - Graz University of Technology
Research Assistant
Institute of Logistics Engineering - Graz University of Technology
Dominik Stadlthanner
Research Assistant
Institute of Logistics Engineering - Graz University of Technology
Michael Schedler
Research Assistant
Institute of Logistics Engineering - Graz University of Technology
Bastian Mayer
Student
Bastian Mayer
Institute of Logistics Engineering - Graz University of Technology
Associate Professor
Institute of Logistics Engineering - Graz University of Technology
A method for pre-sorting mixed mail using convolutional neural networks and transfer learning
Logistics and Intralogistics SystemsSorting mixed mail has become increasingly important for postal service providers. Low-value consignments, that have unfavorable material properties, such as odd shape or flexibility, have increased in terms of volume in recent years and cause substantial problems in sorting processes. In order to automate the sorting of mixed-mail items the so-called ‘Free-Fall-Sorter’ was developed at the Institute of Logistics Engineering at Graz University of Technology. In this paper, an image classification system is proposed to pre-sort mixed mail for this new machine. The computer vision system used for the experiments applies transfer learning to a publicly available convolutional neural network called ‘MobileNet V2’. The classification system is designed to be composed of low-cost hardware components, yet capable of providing real-time inference. The results show a high accuracy of the model.
