Image-based system and method for predicting physiological parameters

A method for predicting physiological parameter of a person based on a facial image thereof, comprising:

• receiving a request for body mass index value;
• acquiring an image with at least facial and upper body features of a person;
• processing the image to a frontal facial image;
• applying the frontal facial image, comprising the facial and upper body features, to a trained neural network model to predict weight and height of the person based on the facial and upper body features;
• determining body mass index value based on the predicted weight and height;
• and
• providing, in response to the request, the determined body mass index value;
• and wherein
• said trained neural network model is a regression deep learning convolutional neural network model.

A non-transitory computer readable medium including a set of instructions that are executable by one or more processers of a computer to cause the computer to perform a method for predicting body mass index value based on a facial image of a person, the method comprising:

• receiving a request for body mass index value;
• acquiring an image with at least facial and upper body features of a person;
• processing the image to a frontal facial image;
• applying the frontal facial image, comprising the facial and upper body features, to a trained neural network model to predict weight and height of the person based on the facial and upper body features;
• determining body mass index value based on the predicted weight and height;
• and
• providing, in response to the request, the determined body mass index value;
• and wherein
• said trained neural network model is a regression deep learning convolutional neural network model.

A system for predicting physiological parameter of a person based on a facial image thereof, comprising:

• an image processor, electrically coupled with a network, said image processor being configured for:
• receiving from a digital device a captured image including upper body features of a person;
• said upper body features including a face and a neck and shoulders of said person, and said upper body features excluding body features that are lower than said shoulders of said person;
• pre-processing said captured image to generate a pre-processed image, said pre-processed image being a frontal facial image, said frontal facial image including said upper body features, and said frontal facial image further excluding body features that are lower than said shoulders of said person;
• providing said pre-processed image as input into to a trained neural network model, said trained neural network model being configured to predict weight and height of the person based on said pre-processed image;
• and
• receiving a predicted weight and height of the person from the neural network model.