E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text
This addresses the challenge of multi-language OCR for scene text, though it is incremental as it builds on existing end-to-end approaches.
The authors tackled the problem of multi-language scene text localization and recognition by proposing E2E-MLT, an end-to-end trainable method based on a fully convolutional network, which demonstrated competitive performance compared to English-only methods.
An end-to-end trainable (fully differentiable) method for multi-language scene text localization and recognition is proposed. The approach is based on a single fully convolutional network (FCN) with shared layers for both tasks. E2E-MLT is the first published multi-language OCR for scene text. While trained in multi-language setup, E2E-MLT demonstrates competitive performance when compared to other methods trained for English scene text alone. The experiments show that obtaining accurate multi-language multi-script annotations is a challenging problem.