GSoC 2022 Project: Improving the Visual Recognition of Aztec Hieroglyphs (Decipherment Tool)
Our aim is to enlarge the data set with added iconographic and hieroglyphic examples from other manuscript sources. A larger dataset will help us test the accuracy and improve the grade of matching with respect to users’ tests (uploading hieroglyphs for mechanical decipherment). We will also establish a protocol of action and behavior between hieroglyphic texts and the previously created Machine Learning prototype. Finally, the results will be linked to potential entries in the Visual Lexicon dictionary and, in turn, the Online Nahuatl Dictionary where end-users can learn more about their images under study their visual characteristics and linguistic meanings.
GSoC 2021 Project: Depicting of Graphical Communication Systems (GCS) in Aztec/Central Mexican manuscripts with Deep Learning: glyphic visual recognition and deciphering using Keras
Among all the human writing communication systems and inspired by Google Arts & Culture project Fabricius, we propose the creation of a framework to identify glyphs in Aztec/Central Mexican codex and classifying their Graphical Communication System (GCS) using Convolutional Neural Networks (CNN).
Aztec Codex & Visual Recognition
The Visual Recognition of Aztec Hieroglyphs and its mirror URL are based on Visual Lexicon of Aztec Hieroglyphs ed. Stephanie Wood, focused in early 16th-century Mendoza Codex from Mexico and related, such as Matrícula de Tributos.