Introduction

You are currently viewing the documentation for the latest version (2.6.2). To access a different version, click the "Switch version" button located in the upper-right corner of the page.

■ If you are not sure which version of the product you are currently using, please feel free to contact Mech-Mind Technical Support.

In Mech-DLK, you can connect multiple algorithm modules to train models for more complex on-site needs. In this example, the cascade of Text Detection and Text Recognition algorithm modules is used to demonstrate the usage of cascaded modules.

Use Cascaded Modules

First, confirm whether the dongle rights include the module cascading function by clicking the + sign in the upper-right corner of the Modules section. If you can click it, the function is enabled. If not, please contact Mech-Mind Sales to upgrade the authorization version.

alt
  1. Create a Text Detection project

    Follow Use the Text Detection Module to complete the training and validation of the Text Detection model.

  2. Create a Text Recognition project

    Click + and select the Text Recognition module to add.

    cascaded module add project
  3. Import the data from the previous module

    Click the Import/Export button and select Import from Previous Module to use the training results from the Text Recognition module as input.

    1. Click Import/Export and select Import from Previous Module.

      cascaded module import
    2. In the Import window, select the images of the Text Recognition module that you want to import. You can also filter images by using Min confidence and Image tag.

      cascaded module select
    3. Modify Import Configuration.

      • Expand by: Expand the imported images by a specified number of pixels. The expansion can prevent data loss caused by insufficient accuracy of the previous module. Default value: 0 px

      • Rectify image(s): Rectify all imported images to the positive direction (0°).

      • Options for duplicates: You can choose to skip or import duplicate images.

      • Image tag: Use existing tags or add new ones as needed.

        The Import Configuration may vary under different cascaded modules. Please set the parameters according to what is displayed.
    4. Click OK.

  4. Perform labeling and training in the Text Recognition module

    Complete the labeling and training of the current module.

  5. Validate and export the model

    After training, validate the model and export it. The exported model can be used in Mech-Vision and Mech-DLK SDK.

    Cascaded models can only be used in Mech-Vision version 1.7.2 or above, but below version 2.0.0.
If the previous module is updated, the following module needs to be re-trained.

Is this page helpful?

You can give a feedback in any of the following ways:

We Value Your Privacy

We use cookies to provide you with the best possible experience on our website. By continuing to use the site, you acknowledge that you agree to the use of cookies. If you decline, a single cookie will be used to ensure you're not tracked or remembered when you visit this website.