OCR Models
TrOCR
Introduced by Li et al. in TrOCR: Transformer-based Optical Character Recognition with Pre-trained ModelsTrOCR is an end-to-end Transformer-based OCR model for text recognition with pre-trained CV and NLP models. It leverages the Transformer architecture for both image understanding and wordpiece-level text generation. It first resizes the input text image into $384 × 384$ and then the image is split into a sequence of 16 patches which are used as the input to image Transformers. Standard Transformer architecture with the self-attention mechanism is leveraged on both encoder and decoder parts, where wordpiece units are generated as the recognized text from the input image.
Source: TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Optical Character Recognition (OCR) | 7 | 33.33% |
| Decoder | 2 | 9.52% |
| Language Modeling | 2 | 9.52% |
| Language Modelling | 2 | 9.52% |
| Handwritten Text Recognition | 2 | 9.52% |
| Image Generation | 1 | 4.76% |
| Image Captioning | 1 | 4.76% |
| Large Language Model | 1 | 4.76% |
| Adversarial Attack | 1 | 4.76% |
Layer Normalization
Multi-Head Attention
Residual Connection
Scaled Dot-Product Attention
