TEIMMA: The First Content Reuse Annotator for Text, Images, and Math.
Ankit SatputeAndré Greiner-PetterMoritz SchubotzNorman MeuschkeAkiko AizawaBela GippPublished in: CoRR (2023)
Keyphrases
- web images
- text information
- semantic content
- image analysis
- image data
- image database
- textual information
- image classification
- image registration
- object recognition
- ground truth
- image regions
- three dimensional
- feature points
- image retrieval
- image annotation
- keywords
- text detection
- text mining
- input image
- multimedia documents
- text content
- complex background
- text extraction
- textual content
- textual descriptions
- metadata
- digital content
- lighting conditions
- text documents
- image matching
- visual features
- multiscale
- multimedia