NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition

3 code implementations • 4 Jun 2018 • Fenfen Sheng, Zhineng Chen, Bo Xu

Considering scene image has large variation in text and background, we further design a modality-transform block to effectively transform 2D input images to 1D sequences, combined with the encoder to extract more discriminative features.

Decoder Optical Character Recognition (OCR) +1