Abstract: Various embodiments described herein provide techniques for analyzing an image (e.g., a selfie) of a user with one or more pre-trained machine learned models, to detect facial characteristics of the user. Then, using the output of the machine learned model(s), various combinations of detected facial characteristics are used to assign the user with one style profile of several predefined style profiles. Finally, the style profile may be used in the selection of one or more products to be recommended to the user.

Abstract: In some examples, a method includes using at least one processor, accessing image data representing an image of a face of a user, identifying a facial feature of the user using the image data, using the at least one processor, automatically matching the facial feature to a matched pattern of a plurality of patterns, based on configured pattern lookup rules, identifying a product depiction, from a plurality of product depictions stored in product database, based on the matched pattern of the plurality of patterns, and causing display of the product depiction on a user interface.

Abstract: Various embodiments described herein provide for a method that comprises: accessing an image representing a face of a user; identifying a base color of the user's face based on the image; matching the base color of the user's face to a color palette based on configured color lookup rules; identifying a product depiction, from a plurality of product depictions stored at an ecommerce server, based on a color of the product being included in the color palette; and causing the display of the product depiction on a user interface.