Emoji-based communications derived from facial features during game play

A system for generating emoji models based on user facial features, the system comprising:

• a memory;
• a camera that captures a plurality of images of a user, the images captured at determined times during gameplay;
• and
• a processor that executes instructions stored in the memory, wherein execution of the instructions by the processor:
• extracts one or more facial feature landmarks detected within each captured image based on facial recognition of one or more facial features of the user;
• tracks a position of each of the facial feature landmarks in each captured image, wherein a set of positions of the facial feature landmarks correspond to a facial expression in the captured image;
• identifies a corresponding facial expression based on a change in the position of the tracked facial feature landmarks across the captured images;
• selects at least one of the captured images to use in mapping the corresponding facial expression;
• maps the tracked facial feature landmarks within the at least one selected image to a model emoji, wherein the model emoji is associated with the corresponding facial expression;
• adjusts one or more portions of the model emoji based on a weight for one or more of the facial features of the user;
• and
• distributes the adjusted model emoji over a communication channel to one or more recipients associated with a current session of the user.

A non-transitory, computer-readable storage medium, having instructions encoded thereon, the instructions executable by a processor to perform a method for generating emoji models based on user facial features, the method comprising:

• capturing a plurality of images of a user, the images captured by a camera at determined times during gameplay;
• extracting one or more facial feature landmarks detected within each captured image based on facial recognition of one or more facial features of the user;
• tracking a position of each of the facial feature landmarks in each captured image, wherein a set of positions of the facial feature landmarks correspond to a facial expression in the captured image;
• identifying a corresponding facial expression based on a change in the position of the tracked facial feature landmarks across the captured images;
• selecting at least one of the captured images to use in mapping the corresponding facial expression;
• mapping the tracked facial features within the at least one selected image to a model emoji, wherein the model emoji is associated with the corresponding facial expression;
• adjusting one or more portions of the model emoji based on a weight for one or more of the facial features of the user;
• and
• distributing the adjusted model emoji over a communication channel to one or more recipients associated with a current session of the user.