Inverse Scene Text Removal
This work addresses misuse risks of STR by enabling detection of potential tampering, which is incremental as it builds on existing STR methods.
The paper tackles the problem of detecting and localizing removed text in images that have undergone scene text removal (STR), achieving high accuracies in binary classification and region localization, and explores the difficulty of recovering the removed text content.
Scene text removal (STR) aims to erase textual elements from images. It was originally intended for removing privacy-sensitiveor undesired texts from natural scene images, but is now also appliedto typographic images. STR typically detects text regions and theninpaints them. Although STR has advanced through neural networksand synthetic data, misuse risks have increased. This paper investi-gates Inverse STR (ISTR), which analyzes STR-processed images andfocuses on binary classification (detecting whether an image has un-dergone STR) and localizing removed text regions. We demonstrate inexperiments that these tasks are achievable with high accuracies, en-abling detection of potential misuse and improving STR. We also at-tempt to recover the removed text content by training a text recognizerto understand its difficulty.