Acne Result Scheme

Haut.AI provides an AI algorithm that estimates acne-like spots for different facial areas and the whole face.

Description

Acne Algorithm

algorithm_tech_name

acne

area_name

The algorithm returns metrics and sub-metrics for the following facial areas:

• face

• nose_bridge

• right_cheek_large

• left_cheek_large

• forehead_n_bridge

• chin_wide

main_metric

The main metric is an overall score indicating acne spots for each area_name

"main_metric": {
                "value": 100,
                "widget_type": "bad_good_line",
                "name": "Acne score",
                "tech_name": "acne_score",
                "widget_meta": null
            },

• value the acne score ranges from [0,100]The higher the value of this parameter, the fewer acne spots and pimples you have.

• The score can be classified into six classes based on value:

  • (90,100] - Excellent

  • (80,90] - Great

  • (70,80] - Good

  • (50,70] - Average

  • (30, 50] - Poor

  • [0,30] - Bad

• "widget_type": "bad_good_line" indicates that a higher value is better

• "name": "Acne score"

• "tech_name": "acne_score"

sub_metrics

The algorithm returns sub-metrics for each area_name

"sub_metrics": [
                {
                    "value": 0,
                    "widget_type": "numeric",
                    "name": "Number of acne regions",
                    "tech_name": "number_of_regions",
                    "widget_meta": null
                },
                {
                    "value": 0,
                    "widget_type": "density",
                    "name": "Acne regions density score",
                    "tech_name": "density_score",
                    "widget_meta": null
                },
                {
                    "value": 0,
                    "widget_type": "density",
                    "name": "Average intensity of acne regions",
                    "tech_name": "average_intensity_score",
                    "widget_meta": null
                }
            ]

• Number of acne regions estimates the number of detected acne spots

  • value the detected number of spots

  • "widget_type": "numeric"

  • "name": "Number of acne regions"

  • "tech_name": "number_of_regions"

• Acne regions density score estimates the density of spots

  • value the density of acne spots

  • "widget_type": "density"

  • "name": "Acne regions density score"

  • "tech_name": "density_score"

• Average intensity of acne regions estimates the intensity of acne spots

  • value the higher the value of this parameter, the more severe the spots

  • "widget_type": "density"

  • "name": "Average intensity of acne regions"

  • "tech_name": "average_intensity_score"

masks_restored

The algorithm returns a vectorized mask of acne regions for a face-aligned image

• "mask_type": "polygon_mask"

• features

  • geometry

    • "type": "MultiPoint"

  See more on Masks here

masks_original

The algorithm returns a vectorized mask of acne regions for an original image

• "mask_type": "polygon_mask"

• features

  • geometry

    • "type": "MultiPoint"

  See more on Masks here

Example (JSON)

23KB

acne.json

Open

acne.json