A method and system for detecting and identifying multiple surfaces of cigarette cartons in storage or display scenarios

Abstract

The present application relates to a method and system for multi-faceted detection and identification of cigarette cartons in inventory or display scenarios, which includes obtaining images of cigarette cartons in inventory or display scenarios; processing the images through a neural network; obtaining the number and / or brand information of cigarette cartons; detecting whether a new image appears, and if so, repeating the above steps to process the new image. When the present application collects information about cigarette cartons in inventory or display scenarios, it has the characteristics of being able to automatically identify and unify information, thereby reducing the trouble of manually collecting information and improving the efficiency of information collection.

Images