LandingLens FAQ
  • 21 Mar 2023
  • 3 Minutes to read
  • Dark
    Light
  • PDF

LandingLens FAQ

  • Dark
    Light
  • PDF

Image FAQs

How many images do I need to upload for model training?

Since every use case is different, there is no one number that works in every situation. This number generally depends on these factors:

  • How elaborate the object to identify is
  • How many types of objects there are
  • How the object looks

For example, a hammer with a broken handle would require fewer images than a printed circuit board that has several intricate parts.

Tips for Object Detection Projects

Models in Object Detection Projects learn based on the contents of the bounding boxes (the areas you identify as the Ground Truth). Therefore, it's important to get a well-represented spread of bounding boxes for each Class. 

For complex projects (like circuit boards), we recommend you include a minimum of 50 bounding boxes per Class. If one image has five bounding boxes, then this counts as five, not one.

Tips for Classification Projects

Each image can only have one Class applied to it. Therefore, if an image meets the criteria for more than one Class, we recommend that you don't include it in training because it could confuse the Model. 

For complex projects (like circuit boards), we recommend you include a minimum of 50 images per Class. 

Tips for Segmentation Projects

Models in Segmentation Projects learn based on the specific pixels marked by the lines or shapes you add to the images (the areas you identify as the Ground Truth). 

Therefore, it's important to get a well-represented spread of marked areas for each Class.

Typically, a Segmentation Project requires fewer images than an Object Detection Project. This is because a Segmentation Project allows you to label areas more precisely.

For complex projects (like circuit boards), we recommend you include about 20 to 30 labeled areas per Class. If one image has five labeled areas, then this counts as five, not one.

What image file types does LandingLens support?

LandingLens supports BMPs, JPEGs, and PNGs for all Project Types. 

Object Detection also supports Pascal VOC files. Pascal VOC (Visual Object Classes) is a file format that includes the label details of its paired image. It essentially tells the platform where a label is on the associated image.

Labeling FAQs

What types of labeling tools are available?

LandingLens offers different Project Types, and each Project Type has a different labeling tool.

Project TypeLabel Tool
Object DetectionBounding boxes (rectangles) to outline an object.
SegmentationPen-like tools to "paint" specific pixels.
ClassificationClassify images after upload using Classes. Or, upload "classified" folders; LandingLens will automatically classify images based on the titles of the folders. (Classification looks at all the pixels in an image.)
Anomaly DetectionSeparately upload "normal" and "abnormal" images. Similar to Classification, Anomaly Detection considers all pixels in an image.
Note:
Anomaly Detection is only available to legacy "classic" workflow users.

Do you have tools to evaluate consistency among different Labelers?

Yes! LandingLens offers Agreement-Based Labeling that allows multiple Labelers to label the same images. The platform will then rank those images based on levels of consistency. For more information, go here.

What types of augmentation tools are available?

LandingLens offers these augmentation tools:

  • Random brightness
  • Blur, motion blur, and gaussian blur
  • Hue saturation
  • Random contrast
  • Horizontal and vertical flips
  • Random rotate
  • Random augmentation

For more information about how to apply these tools, go to Data Augmentation.

Upload FAQs

Can I upload pre-labeled images to LandingLens?

Yes! Pre-labeled image files must be in a Pascal VOC file format. Pascal VOC (Visual Object Classes) is a file format that includes the label details of its paired image. It essentially tells the platform where a label is on the associated image. For more information, go to Upload Pre-Labeled Images

Can I upload zipped files to LandingLens?

All files must be unzipped before uploading them to LandingLens.

Does LandingLens keep folder hierarchies on upload?

LandingLens simplifies folder structures and flattens all files. Let's say you have one folder (Folder A) and two subfolders (Folder B and Folder C). If you upload Folder A, LandingLens will upload all images from Folders A, B, and C, as if they came from the same folder.

LandingLens Flattens Files 

However, if you are uploading Classified Media to a Classification Project, LandingLens will ignore any subfolders. Referring back to the example above, if you upload Folder A, only the images in Folder A will be uploaded; the images in Folders B and C will not be uploaded. 

LandingLens Ignores Subfolders for Classified Media Uploads

 


Was this article helpful?