The article delves into the implementation of an image classification system using deep learning to automatically detect and classify images of Indian cities. The study focuses on classifying images of Ahmedabad, Delhi, Kerala, Kolkata, and Mumbai based on distinct features. Two approaches were adopted - a vanilla Convolutional Neural Network (CNN) and transfer learning with the VGG16 model. The VGG16 model achieved a test accuracy of 63.6%, showcasing the potential for real-time location identification systems. The research aims to contribute to tourism, urban planning, and other applications by recognizing city imagery's unique characteristics.
To Another Language
from source content
arxiv.org
Key Insights Distilled From
by Anjali Karan... at arxiv.org 03-19-2024
https://arxiv.org/pdf/2403.10912.pdfDeeper Inquiries