The invention relates to a method and a system for reading coded information from an object. The system comprises one or more three-dimensional cameras configured such as to capture three-dimensional images of the object and a processor configured such as to process the captured three-dimensional images. The processor is designed to: identify planes upon which faces of the object lie; extract two-dimensional images that lie on the identified planes; and apply coded information recognition algorithms to at least part of the extracted two-dimensional images.