Deep Model Customizer
      Back to home
      1. Aiconix Knowledge Base
      2. Deep Model Customizer

      What is the Face Training?

      Easily train your custom dataset for the face recognition.

      Module Description

      Our Deep Model Customizer with its Face Training module simplifies the process of training new faces for facial recognition. Using highly effective few-shot learning, new classes are created in seconds. This requires only a few training images and no negative training data. Our algorithms have been designed to train in the most efficient way possible.

      The feature is simple and intuitive to use, no expertise is required. The image can either be uploaded directly or it can be extracted automatically from the videos using the Face Dataset Creation feature. Face Training works with just a few images and is the perfect complement to the corresponding Face Recognition module.

      How does it work?

      1. Select the "Dataset" module in the vertical menu on the left - it shows an icon with a box on it.
      2. Create a new Face Recognition Dataset. A dataset can be all persons of a project or a parliament.
      3. Create Classes in the Dataset. Each class is one specific person.
      4. Evaluate the finished Dataset. Giving you feedback on the quality.
      5. Train the Model. This makes it available for Recognition
      6. Use the trained Model. In the Face Recognition Module of the Deep Media Analyzer.

      Custom Dataset Types:
      The following dataset types can be custom trained in the Deep Model Customizer:

      • Faces, for building regional face recognition models
      • Speaker, for builging regional voice identification models
      • Landmark, for recognizing regional buildings
      • Logo, for identifying custom logos.

      How to create a new class?

      Once you have opened a Face Training dataset, you can create new classes or edit existing ones.
      When you create a new class, you will need to add certain information:

      • Class name: Label of the person you want to recognise, e.g. name or ID.
      • Note: User-defined text, e.g. for versioning or multiple aged versions of the same person.
      • Priority Level: Defines the priority level for the class
      • Expiration Date: When the class should be automatically removed from the dataset.

      How to add training samples to a class?

      Each class needs at least one training image to recognize a person.
      Our face training is based on few-shot learning, which allows us to work with only a few training images, compared to generic models that require thousands of training samples.

      1. For uploading training images, open the class and click "Upload Sample"
      2. Drag and Drop or Select one or multiple training images for this person.
      3. The images now appear in the class as samples, each image is a single sample.

      Each sample can be activated or deactivated using the toggle switch or being edited or deleted via the Three Dots button (...).

      Clustering of Samples:
      Once you uploaded a higher amount of images, the Face Training starts to cluster similar samples and build folders per cluster, for better structuring of the samples. The first folder is always called "Main Cluster". 

      How to evaluate a class?

      Once your classes are ready and contain enough training samples, you want to evaluate the quality of your dataset, before triggering the training. For starting the evaluation, go to the Dataset Overview and click "Evaluate". Depending on the size of the dataset, the evaluation will take some time.

      What are the aspects that are evaluated?

      • Sharpness
        Is the sample image sharp or unsharp? Unsharp images will get a yellow "Blurry Face(s)" warning.
      • Outlier
        Is the image an Outlier? Does the image show a person significantly different than the person in the "Main Cluster"? Outlier will produce a red error notification.
      • Multiple Faces
        Does the image show multiple faces? Samples with multiple faces will get a red "Multiple Faces" error notification.
      • Head Pose
        The face of the person is tilted to far off the camera, making it not suitable for training, the sample gets a red "Head Pose" error.

      A dataset is considered "good" (shown in green) if there are no errors or warnings in the dataset. It is therefore suitable for training an AI model and can be trained.

      Can I train an AI model despite errors and warnings in the dataset?

      Despite errors and warnings, an AI model can be trained from a dataset. The results of the evaluation do not prevent training, but it is still recommended to exclude errors from the training and to take a closer look at warnings.

      How to train a custom AI model?

      There are two ways to start face training on a custom model:

      • If you are in the "Dataset" view: Select the dataset you want to train, click "Train", and provide the necessary information.
      • If you are in the "AI Models" view: Click on "Start Training", enter the necessary information and select a dataset to use as training examples for this model.

      When creating a new Model you are asked the following informations:

      • Model Name: Name of this Model
      • Model Type: Speaker Identification, Face Recognition, Logo Recognition , Landmark Recognition.
      • Model Description: Userdefined text for describing the model.

      Versioning of AI models:
      Versioning of AI Models is done automatically in the "AI Models" view on each AI Model card. The version and history of each model can be found in the top right-hand corner in a grey box with the version number.
      This way you don't need to use the model description field for versioning.

      How use the custom AI Model?

      Once the model has been successfully trained, it will appear as an option in the "Model" drop-down menu when configuring face recognition in the Deep Media Analyzer.