# Object detection

Run the object detection process to determine where the objects are located in a given image.

In this case, an additional file with annotations is required for the model's training set. The annotation stores information about the labels describing the objects in the image and possible additional information, depending on the selected standard.

To view the annotations, go to the Object Detection tab of the Datasets view. In this section, you should see a bounding box around the objects of interest in each image.

Keep in mind: If there is an object in the photo and you do not select it during training, the model will misread the contents of the photo, which will affect its overall precision (accuracy).

Not every uploaded image has been annotated, so select Unannotated images to find all the images without object information. Click on the first one.

You should now be redirected to the image editor, where you can assign classification categories and add detection labels. To learn how to use the image editor, check out the tutorial on our Youtube channel:

To add a new annotation, simply hover the cursor over the image and create a square that covers the entire object. To make this task easier, two guide lines appear from the cursor position.

Once a new bounding box has been drawn, select FLASHLIGHT from the pop-up window next to the bounding box. The pop-up window is a simplified view of the right-hand menu.

Click on the Detection labels button in the right-hand menu or use the E keyboard shortcut to open the detection labels tab (to see all shortcuts, click on the keyboard icon in the right-hand menu).

In the detection labels tab, you can see the currently used categories and unused categories. Here you can also add new categories.

If you make a mistake, you can always change the category or add a new one by clicking on the drop-down button, or remove the label by clicking on the red trash can icon or using the delete key. You can also put the label on the back of the canvas by clicking on the icon next to the trash can button or by right-clicking on the bounding box.

Use the arrows at the top of the page or the A and D keyboard shortcuts to move between images. Go to the next photo.

In the next photo, create the bounding box and mark it as USB_ADAPTER.

The image editor also has an automatic mode that allows you to draw one type of label continuously. To activate this mode, click on the pencil icon at the top of the page or in the pop-up window next to the bounding box. To exit this mode, click on the hand icon at the top of the page or use the H keyboard shortcut.

When all the photos have been marked, return to the dataset. All the images are now annotated.