Text-DIAE: Degradation Invariant Autoencoders for Text Recognition and Document Enhancement.
Mohamed Ali SouibguiSanket BiswasAndrés MaflaAli Furkan BitenAlicia FornésYousri KessentiniJosep LladósLluís GómezDimosthenis KaratzasPublished in: CoRR (2022)
Keyphrases
- text recognition
- text lines
- optical character recognition
- document images
- viterbi algorithm
- hidden markov models
- text documents
- keywords
- information retrieval systems
- document collections
- denoising
- text regions
- web documents
- information retrieval
- multiscale
- tf idf
- computer vision
- retrieval systems
- object recognition
- connected components
- document clustering
- document classification
- semantic information
- wordnet
- text mining
- input image