Stitching as an ancient language

• Main Author: Lim, Cheyanne Hui
• Other Authors: Lana Obraztsova
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2022
• Subjects: Engineering::Computer science and engineering
• Online Access: https://hdl.handle.net/10356/158803
• Institution: Nanyang Technological University

With the rapid advancements in AI and Machine Learning automating tasks has become easier than ever before. The continued work in research and development of machine learning algorithms has made it possible to incorporate AI in day-to-day tasks. This project enables you to be able to add color to an image by recognizing the small symbols in the grid and comparing them to a legend provided. The project could be particularly useful for librarians and historians where it could be used to extract different symbols unique to antique languages. Cryptographers use alternate symbols rather than the normal English alphabets; it could be an equally important asset for cryptographic analysis by picking up unique symbols and clustering them together. The project can be an aid in pattern recognition as well where the same idea of similarity and clustering is followed. It harnesses the power of unsupervised machine learning which makes the provision and ability of large datasets unnecessary. This could be particularly useful as this lifts the dependence on big datasets.