During the prediction, IKOSA AI applications will assign an ID to each found object listed in the analysis job results. The IDs not only determine the order of objects in the CSV or XLSX output but also aid in locating objects within the visualization.

This page explains the unique aspects of the way object numbering works in the visualizations.

Order of the objects on small images

The objects on small images (smaller than a “tile” more on this in the following section) are ordered by a line-dominant scheme. This means the image is read line by line and from left to right when numbering the objects. The object’s relevant point is the upper left corner of its bounding box. Simplified, this can be imagined like this:

Open

Line-dominant object numbering on small images

Object order on large images

Large images are split within the application into tiles (dashed line on the image below). The numbering on each of those tiles follows a line-dominant pattern (described in the previous section). However, neighboring tiles are numbered in sequence from left to right and top to bottom. This can result in a pattern like the one below.

Open

Example of tile-dominant-line-dominant object numbering on multiple tiles

The default tile size for IKOSA AI Applications is 2048 x 2048 Pixels. So, if your image is more significant than 2048 Pixels in any direction, expect your object numbering to follow this pattern.

Numbers are omitted on small objects

When labeling small objects, at some point, their IDs hide them behind their index visualization. To avoid this, a visualization threshold for the object number exists. Numbers will not be displayed if the bounding box is over 5 times larger than the object area.

Limit the number of objects to be numbered at all

When predicting objects on large images or whole slide images (WSI), the predicted number can exceed what can be reasonably analyzed visually. There is a maximum number of objects until which the object numbers for all of them will be displayed. The reason for this is that objects with high indices would require a large size to display their value.

By default, this number threshold is 100.000 objects. So, if your prediction contains more than that, no object number will be shown in the visualization.

If you still have questions regarding your application training, feel free to send us an email at support@ikosa.ai. Copy-paste your training ID in the subject line of your email.

Related articles