A study on methods and classification conditions for building façade materials

• Main Author: Tan, Jessie Huixian
• Other Authors: Tiong Lee Kong, Robert
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Civil engineering
• Online Access: https://hdl.handle.net/10356/145430
• Institution: Nanyang Technological University

Artificial Intelligence (AI) is an interdisciplinary science with advancements in machine learning and deep learning to create a virtual paradigm shift that benefits almost every IT sector. It is all around us without people being aware of it these days. One notable example would be Google, an AI company founded by Larry Page and Sergey Brin in 1998. [1] Some practical implementations of deep learning in AI at Google are speech recognition (Google Assistant), video recommendation on YouTube by studying viewer’s preference as they stream content, as well as image recognition. Google was able to sort through millions of internet images and classify them accurately by learning what was present in the images to achieve image recognition. [2] The aim of this project is to the use of AI for identification and classification of defects on building facade. Various image recognition models will be used to identify the defects on building façade and the engine will automatically evaluate the severity of the defects. The model will be trained using a few image databases with adjustments to determine the most accurate outcome.