The Object Detection component enables the user to detect and draw a bounding box around each object of interest in the image and assigns them a class label.
- Make sure
Intellibot Machine LearningPlugin is installed. Refer
Installing Pluginsdocumentation for details.
Machine Learning. Drag and drop
Object Detectionconnector to
- Save the project on your machine. The ML model will be generated in the same directory.
- To configure Object Detection, expand
Global Objects, right click on
Object Detectionand select
The Object Detection Model screen opens. User has the option to build a new model or work on an existing pre-trained model. The user has to select any of the pre trained model and test the accuracy of the test images by clicking on
To work on a new model the user must select
New Modeland click
- The user will be exposed to the
Object Detection Modelscreen which has the
- Under the
Detailstab, assign a name to the model. The
Descriptionfield is optional.
Traintab exposes images for training. Click on the green + sign, to expose to Image Group. Right click on
Image Groupto upload sample images to train the model. Double click on the image to get it under
The next step is to press the
Altkey and select area which the user wants to detect.
Name the selected image under class (label) name (example- stamp, and sign). The class label will populate on the extreme right end corner under
Once all the image classes have been created, click on the
Get Statusbutton will show the training results with the accuracy percentage.
- Depending on the model accuracy the user can decide to tweak the Object Detection Model settings and retrain the model.
- Click on
Testtab which will help the user to test the created model.
- Click on
Importbutton to add test image(s).
- Click on
Testbutton. The object detection result will be displayed as a box around each object of interest in the image and a class label will be assigned.
Using the Model
- Double click on
Global Objectsto expose the various components under
Drag and drop the
ProcessImagecomponent to the design surface which takes an image as an input and detects the object of interest in the image like stamp or signature.
Connect this component to your automation flow.