TEIMMA: The First Content Reuse Annotator for Text, Images, and Math.
Ankit SatputeAndré Greiner-PetterMoritz SchubotzNorman MeuschkeAkiko AizawaOlaf TeschkeBela GippPublished in: JCDL (2023)
Keyphrases
- web images
- text information
- image database
- image data
- semantic content
- image classification
- image features
- textual information
- image registration
- input image
- multimedia
- ground truth
- text extraction
- image search
- textual content
- text content
- text mining
- web documents
- image analysis
- image retrieval
- image set
- complex background
- image collections
- metadata
- textual descriptions
- automatic annotation
- low level image features
- image regions
- content based retrieval
- image annotation
- test images
- text documents
- web pages
- semantic information
- visual features
- edge detection
- image processing
- e learning