Total-Text
Introduced by Chng et al. in Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition
Total-Text is a text detection dataset that consists of 1,555 images with a variety of text types including horizontal, multi-oriented, and curved text instances. The training split and testing split have 1,255 images and 300 images, respectively.
Source: Convolutional Character NetworksBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
Total-Text
|
MixNet
|
|||
|
Total-Text
|
DeepSolo
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
