Inspector – [Inspect] provides a function to inspect for defects in new images using the training results acquired in the Developer. [Inspect] consists of several sub-tabs, and one sub-tab is for inspecting images using one training result. To inspect using several training results, sub-tabs should be added as many as the number of training results. Whenever a new sub tab is added, a Load Model window appears and users can select the desired training result.

Image List Panel (Images)
Here, the images to be inspected can be imported, and the number and name of the loaded images, the number of labels detected after the inspection, or the corresponding defect class (Detected) are displayed.
: Click here to load designated images.
: Click here to load all images in the designated folder.
: Click here to display a list of currently active sub-tabs. When users click the desired tab, the images in the clicked tab are copied to the current tab. However, images that overlap the current tab are not copied.
: After selecting one or multiple images in the Image List panel, clicking this icon will remove the selected images from the Image List panel.
: It categorizes or filters images according to conditions such as the folder of the image file, the class of label detected, etc.
: Users can search for images in the list by image file name.
Image Panel
This shows all the information except for the True Label in the Image panel of the [Analyze] tab.
Model Information Panel (Model)
Users can check the name and information of the trained model imported when creating the tab.
Inspection Result Adjustment Panel (Overall Threshold)
This is the same as the Inspection Result Adjustment Panel of the [Analyze] tab.
Result Analysis Panel (Overall Results)
Classification
Users can check the number of inspected images (Inspected Images) and the number of images classified for each defect class.
Detection and Segmentation
Users can check the number of inspected images (Inspected Images), the total number of detected defect labels and the number of detected defect labels per class (Detected Labels).
Inspect
When users click the [Inspect] button, the Inspect Progress window appears. A detailed information is the same as the Inspect button of the [Analyze] tab.
Export
When users click the [Export] button, the analysis results are reported as follows for each mode.
Classification
- Text file: This file provides information about the set parameters and the classified class for each image.
- Copy Classified Images:
- All inspected results as images: This creates a folder structure according to the classified results and copies and saves the images used for inspection.
- Users can select whether to export the class activation map result when saving as an image.
Detection
- Text file: This file allows users to check the set parameter information, the total number of detected defects and the number of detected defects for each class.
- Overlayed Images:
- Sorted by with or without ‘Detected’ objects: It separates images in which one or more objects are detected from images in which none are detected, and saves them separately by creating folder structures.
Segmentation
- Text file: This file allows users to check the set parameter information, the total number of detected defects and the number of detected defects for each class.
- Overlayed Images: This saves the image drawn by overlaying the outline of the detected result region with the original image.
- Sorted by with or without ‘Detected’ objects: It separates images in which one or more objects are detected from images in which none are detected, and saves them separately by creating folder structures.
- Raw Data: This is the same as the [Analyze] tab.
- Cropped Patches: This is the same as the [Analyze] tab.
Save or Load Tabs
Users can save the tab which completed the inspection as a file in .srInspectTab format by right-clicking the tab, or clicking the Save Current Tab button in the top right menu. Saved tabs can be loaded by clicking the Add Tab button (
) in Inspect, and then clicking the Load Tab button (
).
