Researchers propose Direct Image Decryption, an end-to-end approach that maps encrypted manuscript images directly to plaintext, bypassing the intermediate transcription stage used in traditional pipelines. Using the Copiale cipher as a case study, the authors compare this joint architecture against the conventional two-stage method of transcription followed by decryption.

  • The proposed method eliminates transcription errors that typically propagate to the final output in traditional pipelines.
  • A synthetic data generation pipeline was built to create large-scale cipher-like training data for the Copiale cipher.
  • Results indicate that joint image-to-plaintext modeling is a promising alternative to traditional transcription-based approaches.