Computer-based body part analysis methods and systems

1 . A computer-implemented body part analysis method, comprising:

an image acquisition step, comprising obtaining one or more digital images of at least one body part of a user, in particular the user's face, captured by an image capturing device;

an image processing step, comprising detecting one or more biometric parameters of the at least one body part in the captured one or more digital images; and

an evaluation step, comprising determining a score for each of one or more physiological characteristics of the at least one body part based on the detected one or more biometric parameters,

wherein the one or more digital images comprise a first digital image with a frontal view of the user's face;

wherein the one or more digital images further comprise a second digital image with a lateral view of the user's face;

wherein the one or more digital images further comprise a third digital image with a facial expression different from the facial expression in the first digital image;

wherein the facial expression in the third digital image is a smiling facial expression or a frowning facial expression;

wherein the facial expression in the third digital image is a smiling facial expression and wherein the one or more digital images further comprise a fourth digital image with a frowning facial expression;

wherein the second digital image with the lateral view shows the user's face approximately at an angle between 20 and 70 degrees;

wherein the image acquisition step further comprises providing instructions to the user for adjusting a lighting, a position of the user's face relative to the image capturing device, a distance of the user's face to the image capturing device and/or an orientation of the user's face relative to the image capturing device; and

wherein the step of providing instructions comprises displaying text, symbols and/or visual indications, such as one or more leading lines, on a display associated with the image capturing device.

2 . The computer-implemented body part analysis method of claim 1 , wherein the one or more biometric parameters are selected from the group comprising:

skin texture, in particular relating to the nose, upper lip, suborbital area and/or cheek; wrinkles, in particular relating to the eye lids, glabella, infraorbital area, chin, crow's feet, marionette wrinkles, nasolabial area, upper lip, radial area and/or forehead;

color, in particular relating to haemoglobin, luminance and/or melanin;

volume, in particular relating to the cheek(s), eye groove and/or midface region; proportions, in particular relating to the distance between nose, upper lip and/or lower lip, the chin width, the lip width and/or the V-shape; and/or

geometry, in particular relating to the eyebrow arch.

3 . The computer-implemented body part analysis method of claim 1 , wherein the one or more physiological characteristics comprise the skin firmness, the skin smoothness, the skin elasticity, the perceived age, the attractiveness and/or the youthfulness of the user.

4 . The computer-implemented body part analysis method of claim 1 , wherein at least one of:

(a) the first digital image with the frontal view of the user's face comprises a neutral facial expression;

(b) the second digital image with the lateral view of the user's face comprises a neutral facial expression;

(c) the third digital image comprises a frontal view of the user's face;

(d) wherein the fourth digital image comprises a frontal view of the user's face;

wherein the angle is between 30 and 60 degrees; or

(e) wherein the angle is at approximately 45 degrees.

5 . The computer-implemented body part analysis method of claim 1 , wherein the one or more digital images are captured using a mobile device, in particular a smartphone, or wherein the one or more digital images are captured using an electronic device incorporated in a smart mirror.

6 . The computer-implemented body part analysis method of claim 1 , wherein the evaluation step is performed using at least one statistical classifier which is configured to map one or more biometric features to a score for one or more physiological characteristics of the at least one body part;

wherein preferably a first statistical classifier is configured to map a first predefined set of biometric features to an attractiveness score and preferably a second statistical classifier is configured to map a second predefined set of biometric features to a youthfulness score, wherein the first and second predefined sets of biometric features preferably overlap partially;

wherein the first predefined set comprise at least one biometric parameter relating to color, in particular relating to haemoglobin, luminance and/or melanin;

wherein the second predefined set comprises at least one biometric parameter relating to wrinkles, in particular relating to the eye lids, glabella, infraorbital area, chin, crow's feet, marionette wrinkles, nasolabial area, upper lip, radial area and/or forehead.

7 . The computer-implemented body part analysis method of claim 6 , wherein the at least one statistical classifier has been trained using a training data set comprising a plurality of images of human faces, a selection of one or more biometric parameters and/or a score for each of one or more physiological characteristics; and/or

wherein the statistical classifier has been trained and/or pre-trained using a publicly available data set, such as SCUT-FBP.

8 . The computer-implemented body part analysis method of claim 7 , wherein a training data set comprises a plurality of images of human faces, a selection of one or more biometric parameters, and/or a score for each of one or more physiological characteristics.

9 . The computer-implemented body part analysis method of claim 8 further comprising training the at least one statistical classifier using the training data set.

10 . The computer-implemented body part analysis method of claim 6 , wherein the at least one statistical classifier is an artificial neural network, in particular a deep neural network.

11 . The computer-implemented body part analysis method of claim 1 , further comprising the steps of displaying the one or more scores on a display associated with the image capturing device; and recommending, to the user, one or more treatments to improve the score associated with the one or more physiological characteristics;

wherein the one or more recommended treatments are ranked by their predicted impact on improving the score associated with the one or more physiological characteristics.

12 . The computer-implemented body part analysis method of claim 1 , further comprising the step of displaying an estimated change of the one or more scores after application of the recommended one or more treatments.

13 . An apparatus comprising means for carrying out the method of claim 1 .

14 . A non-transitory computer-readable storage medium storing a computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method of claim 1 .

15 . A non-transitory computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out the method of claim 1 .