Skip to main content

Want to Make Sense of Hieroglyphs? Try out Google’s Fabricius

translate hieroglyphs with google fabricius
(Imagesource)
Have you ever imagined how people at the time of ancient Egypt used to communicate with each other? They simply used drawings, signs and symbols as the form of written communication famously known as “Egyptian Hieroglyphs” one of the oldest forms of writing! Not everyone could write these hieroglyphs only scribes (writers, sons of wealthy Egyptians) were trained to do so. Even after 5000 years, this languages remains a mystery for those who haven’t studied it. To solve this conundrum Google has launched an AI based tool Fabricius, that will not only help decipher ancient hieroglyphs but it will also help people to make sense and learn about the ancient Egypt’s language.
To celebrate 221st anniversary (July 15th , 2020) of Rosetta stone (a slab of stone from 196BC, has message carved into it in three different types of script that helped scholars to crack the code of hieroglyphs) Google has launched its latest AI powered tool Fabricius, here you can “learn”, “play” and “work” around with hieroglyphs. This is the first digital tool for translating and deciphering hieroglyphs. 

Features of Fabricius: 
Learn:
With the short six easy steps and interactive tools, Fabricius virtual assistant teaches you about the basics of hieroglyph script. The tour begins with taking you back to 1922 to discover who was buried in a mysterious tomb!

  • In the first stage, with the hands on activity the let you trace the hieroglyphs (for easier study) as accurately as you can.
translate hieroglyphs with google fabricius
(Image source) 
  • With the introduction of second stage, tool teaches about the creation of facsimiles (i.e. creation of exact copy of hieroglyphs) to prevent damage.
translate hieroglyphs with google fabricius
(Image source)
  • At stage 3, we have to identify the hieroglyph from a given list of symbols.
translate hieroglyphs with google fabricius
(Image source)
  • Now in the 4th stage, we have to reconstruct the damaged hieroglyphic sign to reconstruct the name of Pharaoh.
translate hieroglyphs with google fabricius
(Image source) 
  • Stage 5 teaches about the order in which they are meant to be read.
translate hieroglyphs with google fabricius
(Image source) 
  • With the final stage 6, this tool enables us to translate a cartouche (the series of hieroglyphic symbols inside an oval frame). And you will discover Tutankhamen’s tomb!
translate hieroglyphs with google fabricius
(Image source)
This tool also provides several interesting facts about hieroglyphs and ancient Egypt between different steps of learning.

Play:
Here, you can translate your own messages and emoji’s into hieroglyphs and see how they would have looked in like in the ancient Egyptians language. Casual consumers can here write unique words in hieroglyphs and can share them with their friends over social media. This way user can imagine how Egyptian hieroglyphs are equivalent to emoji’s. However, Google has stated that this is just for fun purpose and the results might not be academically correct.
translate hieroglyphs with google fabricius
(Image source)

Work: 
With the help of various academics around the world Google has developed set of tools powered by Google’s Machine Learning technology to support academic research, increase accuracy in translation and translation of middle Egyptian hieroglyphs. This artificially intelligent tool will ease the research process, for which,“experts had to dig manually through books upon books to translate and decipher the ancient language--a process that has remained virtually unchanged for over a century.” According to Chance Coughenour, Google Arts and Culture program manager.

According to BBC report, “here in this application users can upload the real life images from artefacts and walls where hieroglyphs are available. These images then can be digitally enhanced to better analyse the symbols. Users can trace the outlines of hieroglyphs, which the software then tries to match up with similar symbols in its database - allowing them to search for different meanings and attempt to decipher findings.”
This software also provides a solution for broken text where researchers can annotate and edit faded symbols that are available in Workbench.
However, this workbench is only developed for desktop only and it is currently not available for mobile devices. This tool is released as an open source as to support the better understanding and future development in the field of study of ancient languages.
What is the technology behind Fabricius?
The main underlying technology behind this software is machine learning and artificial intelligence. To be more precise Google’s AutoML technology and AutoML vision was used to develop a machine learning technology to decode the scripts of hieroglyphs.
The translation process of hieroglyphs works on three phases-
  • Extraction- extracting the hieroglyphs from the uploaded images of artefacts and walls and creating workable facsimiles.
  • Classification: now comes the training part of the neural network for the development of machine learning model to correctly identify over 1000 hieroglyphics.
  • Translation- the final step involves matching workable facsimiles sequences and blocks of text to available dictionaries and published translations to achieve the final result.
This software is being released as an open source platform to improve and increase the both the data available and functionality of the tools.

The aim of this experiment is to increase the awareness and preserve the history and culture of ancient Egypt civilization along with the purpose of increasing the efficiency of translation with the help of machine learning. This project began with the Ubisoft’s research project “TheHieroglyphics Initiative” (developed by Google) to understand the written language of Pharaohs.
Fabricius is named after the father of epigraphy, the study of ancient inscriptions.
Available in English and Arabic, this software can be accessed free on Google’s Art & Culture app for mobile devices and on desktop as well. However, workbench feature for research is only available for desktop. Company believes that Egyptian hieroglyphs is just a starting step for Fabricius, soon this technique will be applied to other ancient languages also!

Comments

  1. what a nice post on my favorite theme, when art, culture blends with technology, it create wonders, good goin, keep it up, my wishes...

    ReplyDelete
  2. MailWasher Pro Crack
    Boris FX Mocha Pro Crack
    Rosetta Stone Crack
    Sylenth1 Crack
    DiskDigger Crack
    Aberrant DSP SketchCassette Crack
    Wow, amazing block structure! How long
    Have you written a blog before? Working on a blog seems easy.
    The overview of your website is pretty good, not to mention what it does.
    In the content!

    ReplyDelete
  3. Great set of tips from the master himself. Excellent ideas. Thanks for Awesome tips Keep it up
    aberrant-dsp-sketch-cassette-crack

    ReplyDelete

Post a Comment

Popular posts from this blog

9 Techniques to Write Your Code Efficiently

(Photo by Oskar Yildiz on Unsplash ) It’s really easy to write efficient and faster code . Efficient code, not just only improves the functionality of the code but it can also reduce the time and space complexity of the programming. Speed is one of the major factors in deciding the quality of the code , for instance, your code might be producing the required result but it takes some time to execute then it will not be considered a quality code. An alternative approach to the same problem producing faster results will be considered better. The code should be clean i.e. comprehensible and readable so that it can be reused (saving the efforts of rewriting the whole program from scratch), adding new features, and making the process of debugging more easier. In this article, I will cover some simple tips and techniques which we can easily apply to make our code more elegant and efficient. "There is always more than one method to solve the problem." How to write code efficie...

Everything You Need to Know About Google Foobar Challenge

Recently, while searching a keyword “headless chrome” on Google I got an unusual pop-up on my window, with a message: "Curious developers are known to seek interesting problems. Solve one from Google?" I was surprised to see Google sending me a challenge to solve and I accepted it immediately! Clicking on “I want to play” landed me on Google’s Foobar page. It was Google Foobar Challenge! What exactly is Google Foobar Challenge? Google Foobar challenge is a secret hiring process by the company to recruit top programmers and developers around the world. And it is known that several developers at Google are hired by this process. The challenge consists of five levels with a total of nine questions , with the level of difficulty increasing at each level. What to do after getting the challenge? After selecting “I want to play” option you land on Foobar’s website which has a Unix-like shell interface, including some standard Unix commands like help, cd, ls, cat and etcetera . ...

Cheatsheet for NumPy: Essential and Lesser-Known Functions

(Photo by  Chris Liverani  on  Unsplash ) Numpy  ( stands for — Numerical Python ) is a library available in Python programming language, supporting matrix data structures and multidimensional array objects. This the most basic scientific computing library that we need to learn, to begin our journey in the field of data science. Numpy can compute  basic mathematical calculations  to make the process of creating advanced machine learning and artificial intelligence applications easier (by using comprehensive mathematical functions available within the library). Numpy allows us to  carry out various complex mathematical calculations effortlessly  along with several top-up libraries (like matplotlib, pandas, scikit-learn, etc.) built over it. This library is a great tool for every data science professional to  handle and analyze the data efficiently . Moreover, it is much easier to perform mathematical operations with numpy arrays in comparison ...

Followers