Image Based Search of Products on Marketplace using Real-World Images

Hingu, Dhwani Dharmesh (2022) Image Based Search of Products on Marketplace using Real-World Images. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (4MB) | Preview
Preview	PDF (Configuration manual) Download (2MB) | Preview

Abstract

To enhance the shopping experience of the customer on e-commerce or market place a lot of development has been encountered with respect to technology. One of the enhancements is searching for products through images instead of text, labels, keywords related to that product. Plethora of researches were carried out under image retrieval domain, among which less number of researches were found based on product image retrieval.Also, no research was found where google open image dataset was used for image retrieval. Thus, this research study aims to use google open image dataset for image retrieval, the dataset has real world crowd-sourced images with 600+ classes. Models like CNN, VG16 and ResNet50 were used for image retrieval, also combinations of these models were used for transfer learning and feature extraction. Among all the experiments carried out VGG16 gave remarkable results with accuracy of 71% on google open image dataset.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TR Photography H Social Sciences > HF Commerce > Electronic Commerce
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	26 Jan 2023 15:51
Last Modified:	26 Jan 2023 15:51
URI:	https://norma.ncirl.ie/id/eprint/6134

Actions (login required)

View Item