...
Name | Definition | Related articles |
---|---|---|
false-positives | a detection error where the algorithm falsely registers the presence of an object | |
false-negatives | a detection error where the algorithm falsely registers the absence of an object | |
ground truth | the annotations in the input image data done by the user. The deep learning model is trained to target morphological structures in novel image data, similar to the ground truth annotations.https://kmlvision.atlassian.net/wiki/spaces/KB/pages/3205070870 | |
image classification | a computer vision task for categorizing groups of pixels or vectors within a given image | |
instance correctness | a metric that gives you information about the ability of the algorithm to correctly detect and label instances in the process of instance segmentation. Instance correctness relies on contour information to estimate the presence of an overlay of annotated and predicted instances. | How to understand instance segmentation qualitative results? |
...
Name | Definition | Related articles |
---|---|---|
pixel correctness | a metric that gives you information about the ability of the algorithm to correctly detect and label instances in the process of instance segmentation. Pixel correctness relies on pixel-level information to estimate the presence of an overlay of annotated and predicted instances. | How to understand instance segmentation qualitative results? |
predicted areas | areas within an image assigned to a particular label | |
predicted pixel label | the label the AI-algorithm assigns a pixel to. This means each pixel in an image is assigned a class label from a predefined set. In other words, the “predicted pixel label“ is the label the AI-algorithm assigned to a specific pixel. | |
random split | the process of letting the platform decide which images are used for training and which ones for validation. | |
RGB images | images that consist of 3 channels: red, green and blue. | |
semantic segmentation | a computer vision task for segmenting an image through assigning a label to each pixel within. |
...