Designing a Vision Transformer based Enhanced Text Extractor for Product Images.
Saptarshi MisraPranay DugarAnirban ChatterjeeLalitdutt ParsaiKunal BanerjeePublished in: COMAD/CODS (2023)
Keyphrases
- image data
- input image
- image database
- image retrieval
- image registration
- image analysis
- object recognition
- ground truth
- textual information
- image classification
- text information
- edge detection
- image collections
- rigid body
- image features
- image regions
- image matching
- lighting conditions
- image set
- web images
- information retrieval
- keywords
- three dimensional
- textual descriptions
- image annotation
- text extraction
- feature points
- image understanding
- region of interest
- test images
- visual information
- single image
- gray level
- vision system
- fuzzy logic
- similarity measure
- image processing