Skip to content

Lower Third Recognition

Module Description

Lower Third Recognition

Lower Third Recognition reads the names displayed on screen text-inserts and associates them to the corresponding person. Create an individual and unique dataset of your own repository of personalities.

For historical reason the Lower Third Recognition module can be used to extract training data from videos. Please use Face Dataset Creation to create your training data from videos with lower thirds.

Module ID: lower_third_recognition

Module Parameters

Name Type Default Description
detect_single_name boolean false Lower Third Recognition is optimized on detecting full names. Enable this to detect single names as well.
apply_generic boolean true Use the generic method to find names
name_dictionary_list List of strings null You can provide a custom names dictionary to detect your custom names. Only names from this list will be detected. Example: ["Angela Merkel", "Markus Söder"]
min_face_size integer 112 Minimum size of the smallest side of the face in pixels
sharpness_threshold integer 40 Minimum quality of the face (lower number is more blurry)
only_faces boolean true Only take lower-thirds into account if a face is visible at the same time. You can explicitly set this to false if you also want to detect name inserts even if no faces are visible.
secondary_dictionaries List of strings null You can provide a list of Dictionary object ID's. These dictionaries will be used to recognice custom name entities. Example: ["70e9f19a-e084-4f93-bae9-85949ba7bfb8", "da05faf8-abdd-411d-b46c-e3d6ad8766ae", ...]. See Dictionary Resource.
dictionaries list of Dictionary Specification objects [ ] List of dictionaries to detect your own keywords/entities in the resulting transcription.


Send the following JSON as request body via POST to the /jobs/ endpoint:

  "sources": [
  "modules": {
    "lower_third_recognition": {}