Eye Area Condition Result Scheme

Haut.AI provides a set of AI algorithms that estimate the condition of the skin in the eye area.

Description

Eye Area Condition Algorithm

algorithm_tech_name

eye_area_condition

area_name

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

  • face

  • left_eye_area_outer

  • right_eye_area_outer

main_metric

The main metric is an overall score that indicates the condition of the skin around the eyes in each area_name

"main_metric": {
                "value": 43,
                "widget_type": "bad_good_line",
                "name": "Eye Area Condition",
                "tech_name": "eye_area_condition",
                "widget_meta": null
            },
  • value The eye area skin condition score ranges from [0,100]. A higher value in this parameter is associated with less prominent eye bags, lacrimal grooves, and dark circles. 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": "Eye Area Condition"

  • "tech_name": "eye_area_condition"

sub_metrics

The algorithm returns three sub-metrics - Dark Circle Score,Eye Bags Score, and Lacrimal Groove Score that evaluate the condition of the skin in the eye area

"sub_metrics": [
                {
                    "value": 42,
                    "widget_type": "bad_good_line",
                    "name": "Dark Circle Score",
                    "tech_name": "dark_circles_score",
                    "widget_meta": null
                },
                {
                    "value": 45,
                    "widget_type": "bad_good_line",
                    "name": "Eyes Bags Score",
                    "tech_name": "eyes_bags_score",
                    "widget_meta": null
                },
                {
                    "value": 47,
                    "widget_type": "bad_good_line",
                    "name": "Lacrimal Groove Score",
                    "tech_name": "lacrimal_groove_score",
                    "widget_meta": null
                }
            ]
  • Dark Circle Score evaluates the presence of dark circles for each area_name

    • value ranges from [0,100].The higher the value of this parameter, the less prominent the dark circles

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

    • "name": "Dark Circle Score"

    • "tech_name": "dark_circles_score"

  • Eyes Bags Score evaluates the presence of eye bags for each area_name

    • value ranges from [0,100].The higher the value of this parameter, the less prominent the eye bags

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

    • "name": "Eye Bags Score"

    • "tech_name": "eyes_bags_score"

  • Lacrimal Groove Score evaluates the presence of lacrimal grooves for each area_name

    • value ranges from [0,100].The higher the value of this parameter, the less prominent the lacrimal groove

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

    • "name": "Lacrimal Groove Score"

    • "tech_name": "lacrimal_groove_score"

masks_restored

The algorithm returns three vectorized masks "name": "Dark Circles Mask","name": "Eyes Bags Mask" and "name": "Lacrimal Groove Mask" for dark circles, eye bags, and lacrimal groove objects on a face-aligned image. All masks are polygon_masks

  • "mask_type": "polygon_mask"

  • features

    • geometry

      • "type": "Multipolygon"

    See more on Masks here

masks_original

The algorithm returns three vectorized masks "name": "Dark Circles Mask","name": "Eyes Bags Mask" and "name": "Lacrimal Groove Mask" for dark circles, eye bags, and lacrimal groove objects on an original image. All masks are polygon_masks

  • "mask_type": "polygon_mask"

  • features

    • geometry

      • "type": "Multipolygon"

    See more on Masks here

Example (JSON)

Last updated