The Optical Subsystem for the Empty Containers Recognition and Sorting in a Reverse Vending Machine

Abstract

A reverse vending machine (RVM) is a machine where people can return empty beverage containers like plastic bottles and cans for recycling taking back a deposit or refund amount. Reverse vending machines are a key part of container deposit systems in Europe and the United States. Waste recognition and sorting in RVM machines can be performed by any of the following procedures: by determining the container material (e.g. using the IR-spectrometer), by recognition of the container type by its shape, or by the barcode identification. These three basic control-procedures make any attempt of the fraud completely impossible. But at the same time, it makes the RVM too expensive. With the modern computer vision technologies, we can design another kind of efficient and non-expensive RVM having the same functionality using energy-efficient IoT MCUs. In this paper, some approaches in computer vision and image processing and their application to the problem of automatic recognition of empty recyclable containers (bottles and cans) and detecting fraud were considered. The list of the available methods and frameworks was shortened because SoC and IoT controllers have memory and computational restrictions. The RVM's task is the classification of the image inside the RVM by three possible classes: PET bottle, aluminum can or fraud (everything that doesn't match PET bottle or can), even if cans or bottles are twisted or jammed. Finally, the performance of image recognition procedures in Python and C ++ languages was analyzed and some methods of efficient image processing and RVM structure enhancements to achieve competitive advantages were proposed.