Ocr-free transcript alignment

Tal Hassner, Lior Wolf, Nachum Dershowitz

Research output: Contribution to journalConference articlepeer-review


Recent large-scale digitization and preservation efforts have made images of original manuscripts, accompanied by transcripts, commonly available. An important challenge, for which no practical system exists, is that of aligning transcript letters to their coordinates in manuscript images. Here we propose a system that directly matches the image of a historical text with a synthetic image created from the transcript for the purpose. This, rather than attempting to recognize individual letters in the manuscript image using optical character recognition (OCR). Our method matches the pixels of the two images by employing a dedicated dense flow mechanism coupled with novel local image descriptors designed to spatially integrate local patch similarities. Matching these pixel representations is performed using a message passing algorithm. The various stages of our method make it robust with respect to document degradation, to variations between script styles and to non-linear image transformations. Robustness, as well as practicality of the system, are verified by comprehensive empirical experiments.

Original languageEnglish
Article number6628826
Pages (from-to)1310-1314
Number of pages5
JournalProceedings of the International Conference on Document Analysis and Recognition, ICDAR
StatePublished - 2013
Event12th International Conference on Document Analysis and Recognition, ICDAR 2013 - Washington, DC, United States
Duration: 25 Aug 201328 Aug 2013


Dive into the research topics of 'Ocr-free transcript alignment'. Together they form a unique fingerprint.

Cite this