Displaying 1 to 3 from 3 results

CTPN - Detecting Text in Natural Image with Connectionist Text Proposal Network

  •    Jupyter

These demo codes (with our trained model) are for text-line detection (without side-refinement part). You need a GPU. If you use CUDNN, about 1.5GB free memory is required. If you don't use CUDNN, you will need about 5GB free memory, and the testing time will slightly increase. Therefore, we strongly recommend to use CUDNN.

label_generator - Training data generator for text detection

  •    Python

The repository contains a set of scripts to implement text detection from screen images. The idea is that we use a Convolutional Neural Network (CNN) to predict a heatmap of the probability of text in an image. But before we can predict anything, we need to train the network with a a set of pairs of images and training labels. We obtain the training data by extracting figures with embedded text from research papers. This is a very involved process and you may want to use the labels that I already generated (you are welcome). We have around 500K good labels extracted from around 1M papers from arXiv and the ACL anthology.