Visual search using artificial intelligence

• Main Author: Wu, Weijie
• Other Authors: Yap Kim Hui
• Format: Final Year Project
• Language: English
• Published: 2019
• Subjects: DRNTU::Engineering::General; DRNTU::Engineering::Electrical and electronic engineering
• Online Access: http://hdl.handle.net/10356/77752
• Institution: Nanyang Technological University

With the development of mobile device, the process of image usage is trending more and more popular. People use their phone for taking photo to save the treasury memories. With the rising of Socio-culture which people share their photos into the social media for daily basis. Photos are become more and more informative to the owner of photo in terms of the content ,location and time that photo was taken. Therefore, the idea of a photo gallery system is purposed. The focus of the photo gallery system is to remove the duplicated images and generate the image information. The project assigned was Visual Search Using deep learning. Specifically, this project aims to explore possible applications using deep learning techniques to build up a system combine with image cluster and image captioning application. This project will focus on finding the best model for image captioning and image clustering. Image processing and natural language processing will be used for both applications. A performance analysis will be followed with the result from several models to select the best model for both of applications. The performance metrices for each application will based on the popular benchmark’s metrics.