mirror of https://github.com/open-mmlab/mmocr.git
1.8 KiB
1.8 KiB
Baseline of segmentation based text recognition method.
Introduction
A Baseline Method for Segmentation based Text Recognition.
[ALGORITHM]
Dataset
Train Dataset
| trainset | instance_num | repeat_num | source |
|---|---|---|---|
| SynthText | 7266686 | 1 | synth |
Test Dataset
| testset | instance_num | type |
|---|---|---|
| IIIT5K | 3000 | regular |
| SVT | 647 | regular |
| IC13 | 1015 | regular |
| CT80 | 288 | irregular |
Results and Models
| Backbone | Neck | Head | Regular Text | Irregular Text | base_lr | batch_size/gpu | gpus | download | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| IIIT5K | SVT | IC13 | CT80 | |||||||||
| R31-1/16 | FPNOCR | 1x | 90.9 | 81.8 | 90.7 | 80.9 | 1e-4 | 16 | 4 | model | log |
Notes:
R31-1/16means the size (both height and width ) of feature from backbone is 1/16 of input image.1xmeans the size (both height and width) of feature from head is the same with input image.