Open Blue-PCB opened 1 year ago
Motivation I hope layout-parser can support the open standard HTML OCR (hOCR) file format that represents document layouts. It would allow easier creation of OCR'ed PDFs and allow for interoperability with other tools.
Related resources hOCR Specification v1.2
Additional context Ocropus hOCR-Tools supports the hOCR format, but hasn't been updated in a while.
Motivation I hope layout-parser can support the open standard HTML OCR (hOCR) file format that represents document layouts. It would allow easier creation of OCR'ed PDFs and allow for interoperability with other tools.
Related resources hOCR Specification v1.2
Additional context Ocropus hOCR-Tools supports the hOCR format, but hasn't been updated in a while.