chenxinpeng/SSD_scene_text_detection

Note

This repository is not being actively maintained due to lack of time and interest. My sincerest apologies to the open source community for allowing this project to stagnate. I hope it was useful for some of you as a jumping-off point.

SSD_scene-text-detection

The note about the original paper: SSD: Single Shot MultiBox Detector can be found here.

This practice is inspired by ssd-plate_detection

The detail of the above code can read my blog: http://blog.csdn.net/u010167269/article/details/52851667, which was written in chinese.

Meanwhile, I have uploaded my training caffemodel to BaiduYun, Google Drive, Dropbox.

• BaiduYun：https://pan.baidu.com/s/1dE0Ok3v
• Google Drive: https://drive.google.com/open?id=0B65vBUruA6N4bzNCSGxTcnEtNjg
• Dropbox: https://www.dropbox.com/s/o3mrsfoiyfp21ou/VGG_scenetext_SSD_300x300_iter_60000.caffemodel?dl=0

Some examples of the scene text detection:

Good Cases

Bad Cases

Note

Currently, I mainly focus on image/video captioning.