HENet: Forcing a Network to Think More for Font Recognition
This work addresses font recognition, a specific challenge in text recognition for applications like document analysis, but it appears incremental as it builds on existing methods with a new module.
The paper tackles the challenging problem of font recognition by proposing HENet, a novel font recognizer with a pluggable HE Block that hides discriminative features to force the network to consider complex features for distinguishing similar fonts, achieving encouraging performance on character-level Explor_all and word-level AdobeVFR datasets.
Although lots of progress were made in Text Recognition/OCR in recent years, the task of font recognition is remaining challenging. The main challenge lies in the subtle difference between these similar fonts, which is hard to distinguish. This paper proposes a novel font recognizer with a pluggable module solving the font recognition task. The pluggable module hides the most discriminative accessible features and forces the network to consider other complicated features to solve the hard examples of similar fonts, called HE Block. Compared with the available public font recognition systems, our proposed method does not require any interactions at the inference stage. Extensive experiments demonstrate that HENet achieves encouraging performance, including on character-level dataset Explor_all and word-level dataset AdobeVFR