Skip to content

LUNA PLATFORM v.5.23.0#

Changes

  • Support for a network disk as an image source ("source_type" parameter) was added to the Estimator task ("/tasks/estimator" resource).

    For this type of source, the following parameters can be specified in the request body:

    • The "path" parameter — absolute path to the directory with images in the container (required);
    • The "follow_links" parameter — enables/disables symbolic link processing;
    • The "prefix" parameter — file key prefix;
    • The "postfix" parameter — file key postfix.

    See an example of using prefixes and postfixes in the "/tasks/estimator" resource.

    When using a network disk as an image source and launching Tasks and Tasks Worker services through Docker containers, it is necessary to mount the directory with images from the network disk to the local directory and synchronize it with the specified directory in the container. You can mount a directory from a network disk in any convenient way. After that, you can synchronize the mounted directory with the directory in the container using the following command when launching the Tasks and Tasks Worker services:

    docker run \
-v /var/lib/luna/current/images:/srv/images

    /var/lib/luna/current/images — path to the previously mounted directory with images from the network disk.

    /srv/images — path to the directory with the images in the container where they will be moved from the network disk. This path should be specified in the request body of the Estimator task (the "path" parameter).

    As in the Estimator task using an S3-like storage as an image source, it is possible to recursively download images from nested bucket directories ("recursive" parameter) and select the type of transferred images ("image_type" parameter). To get correct processing results, it is necessary to use the same type of images (source image, face/body sample).

    See the OpenAPI specification for related examples and more information.

  • Two new image checks for compliance with the ICAO standard were added to the "face_quality" group of checks of "/handlers" and "/verifiers" resources of API and Handlers services — "illumination_uniformity" and "dynamic_range".

    The "illumination_uniformity" check enables you to check the uniformity of the illumination of the face in the image. The ICAO standard recommends the use of color images. When using black and white images, the results may be unexpected. It is recommended to use this check if it is necessary to get results that comply with the ICAO standard. In other cases, you can use the VisionLabs algorithm to check the uniformity of the illumination of the face in the image ("illumination_quality" check).

    The "dynamic_range" check enables you to check the dynamic range of facial skin tone.

    It is not possible to use a sample as an input image for these checks.

    See the detailed description of the checks in the "Face and image parameters" section in the administrator manual.

  • The default (recommended) thresholds were updated for the following checks in the "face_quality" check group and the "/iso" resource:

    Check name Old threshold values New threshold values
    mouth_occluded min=0, max=0.3 min=0, max=0.5
    mouth_open min=0, max=0.64 min=0, max=0.5

    It is recommended to set updated thresholds for these checks in previously created handlers.

  • The execution time of requests for matching bodies was reduced when an event is specified as a reference.

Fixed errors

  • The error was fixed where in the response body of the Estimator task result, the value "raw image" was returned in the "filename" field of the "detections" group instead of the file name.