Lines

Haut.AI provides an AI algorithm that estimates lines-like objects in different facial areas and the whole face.

Description

Lines, also known as wrinkles, appear as a sign of the aging process. As we age and are exposed to adverse environmental factors, the collagen and hyaluronic acid content of our skin decreases, causing the loss of moisture and elasticity. These changes lead to the development of wrinkles and sagging, or downward shifts of the skin causing nasolabial folds, marionette folds, and jowls. Over time, our lines become more prominent, developing from fine lines into deep lines. The higher the value of this parameter, the less prominent lines you have.

"algorithm_tech_name": "lines"

area_name

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

  • face

  • forehead

  • right_eye_area

  • left_eye_area

  • right_cheek

  • left_cheek

main_metric

The main metric is an overall score indicating the severity of lines for each area_name

"main_metric": {
                "value": 13,
                "widget_type": "bad_good_line",
                "name": "Lines Score",
                "tech_name": "lines_score",
                "widget_meta": null
            },
  • value the wrinkles score in the range [0,100].The higher the value of this parameter, the fewer lines you have. Lines 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": "Lines score"

  • "tech_name": "lines_score"

sub_metrics

The algorithm returns sub-metrics for "area_name": face only

"sub_metrics": [
    {
        "value": 45,
        "widget_type": "bad_good_line",
        "name": "Sagging Score",
        "tech_name": "sagging_score",
        "widget_meta": null
    },
    {
        "value": 2,
        "widget_type": "numeric",
        "name": "Jowls Grade",
        "tech_name": "jowls_grade",
        "widget_meta": null
    }
]
  • Sagging Score evaluates the severity of face sagging

    • value The sagging severity score in the range [0, 100]. The higher the value of this parameter, the more pronounced the sagging of the skin is.

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

    • "name": "Sagging Score"

    • "tech_name": "sagging score"

  • Jowls Grade evaluates the severity of the jowls - sagging skin below the jawline

    • value the grade of jowls severity in range [1, 4]. The higher the grade, the more pronounced the jowls are.

    • "widget_type": "numeric"

    • "name": "Jowls Grade"

    • "tech_name": "jowls_grade"

masks_restored

The algorithm returns several vectorized masks of wrinkles for a face-aligned image

  1. Deep Lines Mask

    1. "mask_type": "polygon_mask"

    2. "tech_name": "deep_lines_mask_restored"

    3. features

      • geometry

        • "type": "Multipolygon"

  2. Line Lines Mask

    1. "mask_type": "polyline_mask"

    2. "tech_name": "line_lines_mask_restored"

    3. features

      • geometry

        • "type": "Multipolyline"

  3. Sagging Mask

    1. "mask_type": "polyline_mask"

    2. "tech_name": "sagging_mask_restored"

    3. features

      • geometry

        • "type": "Multipolyline"

  • See more on Masks here

masks_original

The algorithm returns several vectorized masks of wrinkles for an original image

  1. Deep Lines Mask

    1. "mask_type": "polygon_mask"

    2. "tech_name": "deep_lines_mask_original"

    3. features

      • geometry

        • "type": "Multipolygon"

  2. Line Lines Mask

    1. "mask_type": "polyline_mask"

    2. "tech_name": "line_lines_mask_original"

    3. features

      • geometry

        • "type": "Multipolyline"

  3. Sagging Mask

    1. "mask_type": "polyline_mask"

    2. "tech_name": "sagging_mask_original"

    3. features

      • geometry

        • "type": "Multipolyline"

See more on Masks here

Example (JSON)

Last updated