The aim of this project is to build an application that can classify seven (7) popular architectural landmarks that can be found in Lagos state, Nigeria. These landmarks include
The data was scraped using the Google Image Scraper tool to extract all the images from Google
-
Extracted the data
-
Arranged and label the data
-
Performed various Data Preprocessing techniques such as converting images into tensors and feature normalization/scaling
-
Convolutional Neural Networks (CNN) using Data Augmentation and Transfer Learning / Pretrained Model to achieved best performance
-
Tuned Inception V3 achieved best performance with 99% training accuracy and 97.2% test accuracy
Accuracy with Confusion Matrix was used to evaluate performance.
- Tuned Inception V3 with Data Augmentation
The final model with the best score was deployed on a web application built with Streamlit