The Image Classification component enables the user to classify images into various classes also providing accuracy for the same.
- Make sure
Intellibot Machine LearningPlugin is installed. Refer
Installing Pluginsdocumentation for details.
Machine Learning. Drag and drop
Image Classificationconnector to
- Save the project on your machine. The ML model will be generated in the same directory.
- To configure Image Classifier, expand
Global Objects, right click on
The Image Classifier Model screen opens. User can add Image Classes as per the project requirements by clicking on the plus sign next to the
Image Class. For example, let’s add
diseasedas class names. Both the image classes will be available to view under dropdown menu of
Image Classis created, select each image class one-by one and click on
Importbutton to add images for that class. Alternatively, user can capture images from the screen using the
Once the images for all classes are uploaded, the next step is to train the model by clicking on
Trainsection of the Image Classification Model Designer.
Training the Model
Traintab will expose the
Classifier Settingswhich the user can change as per the requirements. Alternatively, the user can train the model with the default settings.
Train. After the model is trained, it will show the model accuracy. The user will be able to see the image classification of test data with respective confidence levels.
Depending on the model accuracy, the user can decide to tweak the
Classifier Settingsand retrain the model.
Testing the Model
- Click on
Testtab to test the created model with test data.
- Click on
Capturebutton to add the test image(s).
Testbutton. The classification result will be displayed under the image.
Close the Image Classification Model Designer.
Using the Model
- Double click on the
ImageClassifierunder Global Objects to expose the various components under
- Drag and drop the
ClassifyImagecomponent to the Design Surface which takes an image as an input and returns the class and confidence predicted by the model.
- Connect this component to your automation flow.