The Loracrafft Project

image (c) Antoine Morandi




The goal of the Loracrafft project (with two "f") is to build a php/Python application (a proof of concept) which will be available on the Web to translate, from images, texts written in Middle Empire Egyptian Hieroglyphs (to start with) into French and English.

Initially, the images will be provided by the user via an upload. Secondly, they could come from snapshots taken with a smartphone, when the application is converted into a language running on Android and macOS.

The project is divided into phases as follows:

phase 1: availability of source texts

  • painting on walls

  • walls engraving

  • stone engraving

  • painting on papyrus

  • painting on ostraca

  • painting on wood

  • photos


phase 2: conversion of the source text into high-quality images to be processed by the machine (computer, tablet, smartphone, etc.)

phase 3: identification of the sign which gives the reading direction

phase 4: recognition of signs in groups

phase 5: grammatical classification

phase 6: cutting into words

phase 7: conversion of words into MdC codes

phase 8: transliteration

phase 9: translation into English

phase 10: audio reading of the resulting text

The idea behind the design of this application is to federate already existing "building blocks" to achieve some of the above phases:

For phase 4, we are thinking of the Tomb Reader tool by Morris Franken & Jan van Gemert

For phases 5 and 6, we plan to follow the work of Serge Rosmorduc

For phases 3 and 7, we are thinking of the Hieroglyphs AI tool from Evgeniy & Alexander Sulimov

For phase 8, such a table already exists, kindly provided by Raymond Monfort

For phase 9, we plan to use Paul Dickson's Dictionary of Middle Egyptian with due authorization

As for phase 10, our computers will do the work without us...

Comments welcome.