-
Your project is really doing a good job and it has inspired me a lot, so I wanted to try it myself and experience the fun of object recognition. Here's how I did it:
First I imported your project and…
-
https://arxiv.org/abs/1507.05717
-
/ufl_scene_text_recognition-master$ make
[ 14%] Built target beam_search
make[2]: *** No rule to make target `liblinear-1.94/blas/blas.a', needed by `ufl_predict_char'. Stop.
make[1]: *** [CMakeFi…
-
https://arxiv.org/pdf/1507.05717.pdf
-
https://paperswithcode.com/paper/towards-accurate-scene-text-recognition-with points to the repo, but I don't see a config file for SRN. Is that implemented here? and if so where is it?
-
In order to improve the accuracy of scene text recognition, some existing methods first rectify the text image（e.g. Iterative Image Rectification） and then recognize text. ABINet does not adopt the m…
-
## 本周任务
* 更换基础卷积网络跑识别，准备数据，刚开始跑起来；
* 看了一篇文献，[An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://arxiv.org/pdf/1507.057…
-
## Reference
- [paper - 2018 - SCAN: Sliding Convolutional Attention Network for Scene Text Recognition](https://arxiv.org/pdf/1806.00578v1.pdf)
## Brief
- Sliding Windows + CNN + Seq2Seq
- Seq2…
-
Hi,
I want to use SSD to recognize text in a particular scene. I made the data set as PASCAL. The object does not know where to write the 'text', or the exact text value.
E.g
``` xml
…
-
SVTP has 645 images, if you carefully read each one, you will find there are around 20 images humans cannot recognize. How can this algorithm get 98.6%??
When seeing such so supervised improvemen…