What Machines See Is Not What They Get: Fooling Scene Text Recognition Models With Adversarial Text Images.
Xing XuJiefu ChenJinhui XiaoLianli GaoFumin ShenHeng Tao ShenPublished in: CVPR (2020)
Keyphrases
- image data
- input image
- image database
- three dimensional
- object recognition
- probabilistic model
- image features
- scene text recognition
- random fields
- image collections
- test images
- text detection
- text information
- complex background
- computer graphics
- web images
- multiple images
- ground truth
- image retrieval
- image classification
- rigid body
- image analysis
- image annotation
- image matching
- image regions
- image registration
- text retrieval
- lighting conditions
- region of interest
- parametric models
- segmentation method
- single image
- model selection
- text extraction
- information retrieval