Improve your understanding of qualitative results in semantic segmentation to gain contextual insights into your output data.

What to expect from this page?

1 Location of visualizations
2 Types of visualizations included
- 2.1 ROI(s) overview
- 2.2 Image and ROI Performance
3 Understanding performance visualizations
4 Related articles

Location of visualizations

Qualitative results for all validation images and ROI(s) are presented in the form of visualizations in separate image files in addition to the PDF report.

Location of visualizations in a ZIP folder with output results

Types of visualizations included

ROI(s) overview

If you have included ROI(s) in your validation images, an overview with a visualization of the ROI(s)' position(s) within the image will be provided.

You can find it in the folder rois_visualizations: [your-image-name]_rois_visualization.jpg.

See an overview with a visualization of the ROI(s)' positions within the image

Please note:

Each ROI has an automatically generated [roi-id] according to the creation date of the ROI.
ROI(s) completely outside of the image are not shown in this file.

Image and ROI Performance

You will also find validation visualizations showing the performance of your trained model for a specific label [your-label-name] within the image or the ROI. They are located in the validation_vis folder.

The image and ROI files are named accordingly:

[your-label-name][your-image-name].jpg - visualization name of an image that contains no ROI(s)
[your-label-name][your-image-name]_[roi-id].jpg - visualization name of a ROI

Understanding performance visualizations

Each of the validation visualizations is divided into four sections:

(1) Input image
(2) Prediction visualization
(3) Annotation visualization
(4) Correctness visualization

Please note: that all visualizations are downscaled to 25 megapixels (MP), if the visualization in the original image size is larger than 25 MP.

Input image (Left upper image)

Shows the input image.

Prediction [your-label-name] (Right upper image)

Shows an overlay of the automated prediction of your trained application on top of the input image.

Annotation [label-name] (Left lower image)

Shows an overlay of your annotations (ground truth) on top of the input image.

Correctness (Right lower image)

Visualizes correctness cases resulting from the automated prediction (compared to manual annotations):

True-positive areas are shown in green.

Areas where the application prediction matches your annotated and labeled areas. In other words, it predicts image/ROI areas correctly.

False-positive areas are shown in red.

Areas that have not been annotated and labeled, yet predicted by your application. In other words, it predicts areas of the image/ROI that should not be predicted.

False-negative areas are shown in blue.

Areas that have been annotated and labeled yet were not predicted by your application.

Now that you have mastered the handling of qualitative results, you are perfectly equipped to gain solid insights from your analysis outputs.

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.

IKOSA Knowledge Base

Semantic segmentation - qualitative results