Edit Image Classes and Tags

You are currently viewing the documentation for the latest version (2.6.1). 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.

This topic describes how to create, modify, and delete the classes and tags of images in the Labeling tab.

Image Class

The image classes are used to classify the recognition targets in the images, such as objects and defects, into different classes.

Create a Class

You can use the following method to create an image class:

  1. In the Labeling tab, click + New on the right side of the Classes section.

  2. In the New Class dialog box that appears, create a class based on the type or feature of different objects.

  • You can create new classes in the Instance Segmentation, Classification, and Object Detection modules. Mech-DLK generates default classes for other modules.

  • Object Detection and Instance segmentation supported instance mode.

  • Object detection, Instance segmentation and Text Detection supported full lock, lock by label type and lock by single instance.

    • For full lock, click lock beside the Statistics.

    • For lock by label type, click lock next to a type of label.

    • For lock by single instance, click lock next to an instance.
create label

Modify a Class

You can use the following methods to modify a class:

Method 1:

  1. In the Classes section, select the class that you need to modify, right-click the class, and select Edit.

  2. In the Edit Class dialog box that appears, modify the class name and color.

edit label 1

Method 2:

  1. In the Classes section, click the color block of a class.

  2. In the Edit Class dialog box that appears, modify the class name and color.

edit label 2

Method 3:

In the Classes section, double-click on a class name to quickly rename the class.

edit label 3

Method 4:

  1. In the Classes section, select the class that you need to modify, right-click the class, and select Merge Into.

  2. Select the new class that you need to merge into to change the class of the current data to the new class.

    If you perform the Merge Into operation after you trained the model, it is recommended that you train the model again.
edit label 4

Delete a Class

Please follow these steps to delete a class:

  1. In the Classes section, select the class that you need to delete, right-click the class, and select Delete.

  2. Click OK in the pop-up dialog box.

delete label 1

Image Tag

With the image tagging function, you can add tags to images and thereby manage massive image data in a centralized manner according to the usage scenarios of images.

Create a Tag

You can use the following method to create an image tag:

  1. In the Image Tag section, click +.

  2. By default, the tag name is imageTag1. To rename the tag, double-click the tag name or right-click the tag and then click Rename.

  3. Repeat the above steps to create more tags.

create tag

Add Tags to an Image

You can use the following method to add tag to an image:

  1. In the image list, click an image or select multiple images.

  2. In the Image Tag section, click the Tag button to the right side of a tag, and the image will be tagged accordingly.

    • Press Ctrl or Shift on the keyboard to select multiple images.

    • The Tagged images attribute indicates the number of images with the tag.

    • In the image list, right-click the tagged image(s) and click Clear tags to clear the tags of the selected image(s).
add tag

Delete the Tag

Select the tag and click image label delete icon to delete it. The tag added to the corresponding image(s) will be cleared once deleted.

delete tag

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.

  • Preference
  • I accept
  • I don't accept