PSENet
PSENet copied to clipboard
Have to maintain high resolution to get good result.
Hi, We have implemented your method using tensorflow. We find that to get good result, we have to resize the image to very big size, so it’s not so efficient in practice. We now use your method to detect large angle long text, for normal text and horizontal long text lines, we have much faster method.
How's the performance on benchmark datasets like ICDAR2015 ? I am also trying to reproduce this work.