TextNet for Text-Related Image Quality Assessment

@inproceedings{Li2018TextNetFT,
  title={TextNet for Text-Related Image Quality Assessment},
  author={Hongyu Li and Junhua Qiu and Fan Zhu},
  booktitle={ICANN},
  year={2018}
}
With the rapid increase of consumer photos, annotating and retrieving such images with text are becoming more significant, which requires optical character recognition (OCR) techniques. However, to predict OCR accuracy, text-related image quality assessment (TIQA) is necessary and of great value, especially in online business processes. With more interests in text, TIQA aims to compute the quality score of an image through predicting the degree of degradation at textual regions. 

Topics from this paper.