Abstract: Methods, systems, and computer programs are presented for capturing color images of items for a machine-learning model. In one method, a request, for adding an item to be visually recognized during sales transactions, is detected at a checkout apparatus. Further, the method includes capturing and storing a color image, by each of one or more cameras of the checkout apparatus, of an examination space when the item is present. Further, the capturing and storing of color images of the item is repeated at different poses until at a predetermined number of color images of the item are captured. Further, the method includes generating, by a processor of the checkout apparatus, additional images of the item by modifying the captured color images. A machine-learning model for item recognition is built by training a machine-learning tool with the captured images and the additional images.

Abstract: Methods, systems, and computer programs are presented for providing a feedback loop to improve object image-based recognition based on transaction data. In one method, instructions are received defining items to be visually recognized by a terminal. For each item, a check is made to determine if item image information is in a global database or if it is a new item. The global database includes item images captured during transactions performed at several terminals. For each item in the global database, item image information is downloaded from the global database. For new items, terminal cameras capture pose images for several poses of the new items, each camera taking an image for each pose. A machine-learning program is trained with the downloaded image information and the pose images, where the machine-learning program performs image-based recognition of the items that are presented at the terminal, based on images captured by the cameras.

Abstract: Methods, systems, and computer programs are presented for capturing color images of items for a machine-learning model. In one method, a request, for adding an item to be visually recognized during sales transactions, is detected at a checkout apparatus. Further, the method includes capturing and storing a color image, by each of one or more cameras of the checkout apparatus, of an examination space when the item is present. Further, the capturing and storing of color images of the item is repeated at different poses until at a predetermined number of color images of the item are captured. Further, the method includes generating, by a processor of the checkout apparatus, additional images of the item by modifying the captured color images. A machine-learning model for item recognition is built by training a machine-learning tool with the captured images and the additional images.