Redness Result Scheme

Haut.AI provides AI algorithms that analyze the overall skin redness and skin irritation for different facial areas and for the whole face.

Description

Redness Algorithm

algorithm_tech_name

redness

area_name

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

  • face

  • forehead

  • nose

  • right_cheek

  • left_cheek

main_metric

The main metric is an overall score that indicates the redness of each area_name

"main_metric": {
                "value": 77,
                "widget_type": "bad_good_line",
                "name": "Redness Score",
                "tech_name": "redness_score",
                "widget_meta": null
            },

  • value the redness score ranges from [0,100] A higher skin redness level is associated with a lower value for this parameter. The redness 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, i.e., 100 corresponds to the absence of red areas on the skin while 0 corresponds to extremely irritated skin

  • "name": "Redness score"

  • "tech_name": "redness_score"

sub_metrics

The algorithm returns two types of sub-metrics - Redness Global Score and Redness Local Score

 "sub_metrics": [
                {
                    "value": 89,
                    "widget_type": "bad_good_line",
                    "name": "Redness Local Score",
                    "tech_name": "redness_local_score",
                    "widget_meta": null
                },
                {
                    "value": 64,
                    "widget_type": "bad_good_line",
                    "name": "Redness Global Score",
                    "tech_name": "redness_global_score",
                    "widget_meta": null
                }

  • Redness Global Score evaluates the degree of global rednesses for eacharea_name

    • value the redness global score ranges from [0,100] A higher skin redness level is associated with a lower value for this parameter

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

    • "name": "Redness Global Score"

    • "tech_name": "redness_global_score"

  • Redness Local Score evaluates the degree of local rednesses (blood vessels, irritation, etc.) for each area_name

    • value the redness local score ranges from [0,100] A higher local redness level of the skin is associated with a lower value for this parameter

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

    • "name": "Redness Local Score"

    • "tech_name": "redness_local_score"

masks_restored

The algorithm returns a vectorized heatmap mask of regions with high redness for a face-aligned image.

  • "mask_type": "heatmap_mask"

  • features

    • geometry

      • "type": "Multipolygon"

    See more on Masks here

masks_original

The algorithm returns a vectorized heatmap mask of regions with high redness for an original image

  • "mask_type": "heatmap_mask"

  • features

    • geometry

      • "type": "Multipolygon"

    See more on Masks here

Example (JSON)

PreviousPores Result SchemeNextSkin tone Result Scheme

Last updated