Alt Text: A Visual Search Model for E-Commerce
Title: A VISUAL SEARCH MODEL FOR AN E-COMMERCE PLATFORM
Caption: Enhancing e-commerce with visual search models
Description: This paper presents a visual search model for an e-commerce platform using convolutional neural networks and DenseNet architecture.

International Journal of Computer Techniques – Volume 12 Issue 2, March 2025

Dr. OKWU, HACHIKARU NGOZI¹, Kilakime, Warikaramu-ere, Bridget²
¹Department of Computer Science, Rivers State University, Nkpolu Port Harcourt, Nigeria
Email: okwuhachikaru@yahoo.com
²Department of Computer Science, Bayelsa State Polytechnic, Aleibiri, Nigeria
Email: kilakimekaramu@gmail.com

Abstract

Online shoppers are faced with difficulties such as searching or finding the right keywords to use in search of a particular product needed or searching through a large database of products to find an exact type or the type of product needed which thereby consumes their resources and time. Researchers over time have solved these problems by creating a visual or reverse image search to ensure that users do not need to have the right keyword to search for a product which also saves time and resources by narrowing the database of the product to the particular class of product needed by the user thereby predicting product close to the user’s wants. Their work suffered some setbacks because errors were found due to some misclassification and computational problems. This research work presents a platform that solves these problems by making use of a Convolutional Neural Network which is a Deep-Learning technique to enable the system to learn and predict from the pattern, shape, and colour of the product inputted by the user and also computational problems by using a DenseNet architecture. A considerable amount of dataset was used to train the model. Object-oriented analysis and design (OO-AD) methodology was used to develop the system. The programming language used for this research is Java.

Keywords

E-Commerce, Visual Search, Machine Learning, Neural Network, Deep Learning, Convolutional Neural Network.

References

Aizawa P. and Ogawa M. (2015). “Foodlog: Multimedia tool for healthcare applications”. IEEE MultiMedia, 22(2):4-8.
Bengio, Y. and LeCun, Y. (2007). Scaling learning algorithms towards AI. In Large Scale Kernel Machines, 19.
Clough, P. and Eleta, V. Investigating Language Skills and Field of Knowledge on Multilingual Information Access in Digital Libraries. International Journal of Digital Library Systems (IJDLS), 1(1), 89–103.
Delalleau, O. and Bengio, Y. (2011). Shallow vs. deep sum-product networks. In NIPS. 19, 556.
Hagen, P., Manning H. and Paul, Y. (2000) Must Search Stink? The Forrester Report. June.
Hinton, G. and Shallice, T. (1991). Lesioning an attractor network: investigations of acquired dyslexia. Psychological review, 98(1), 74.
Murdock, V., Kelly, D., Croft, W., Belkin, N., and Yuan, X. (2007). Identifying and Improving Retrieval for Procedural Questions, Information Processing and Management, 43, 1, 181–203.
Pascanu, R., Gülçehre, Ç., Cho, K., and Bengio, Y. (2014). How to construct deep recurrent neural networks. In ICLR’2014. 19, 199, 265, 398, 399, 400, 412, 462.
Shankar Devashish, Narumanchi Sujay, Ananya H.A., Kompalli Pramod and Krishnendu Chaudhury. (2017). Deep learning based large scale visual recommendation and search for E-Commerce. http://arxiv:1703.02344v1. CS-CV.
Yamaguchi K., Kiapour M., Ortiz L., and Berg T. (2015) Retrieving similar styles to parse clothing. IEEE Trans. Pattern Anal. Mach. Intell., 37(5):1028-1040.
Ren S., He K., Girshick R., and Sun J. (2015) Faster R-CNN: Towards real-time object detection with region proposal networks. In Neural Information Processing Systems (NIPS).

How to Cite

Dr. OKWU, HACHIKARU NGOZI, Kilakime, Warikaramu-ere, Bridget, “A VISUAL SEARCH MODEL FOR AN E-COMMERCE PLATFORM,” International Journal of Computer Techniques, Volume 12 Issue 2, March 2025 . ISSN 2394-2231.