Recommendation System using Content Based Visual Similarity

EasyChair Preprint no. 4930

Abstract

A smart search engine presented for online shopping. Basically it uses images as its input, and tries to understand the information about products from these images. First use a neural network to classify the input image as one of the product categories. Then use another neural network to model the similarity score between pair images, which will be used for selecting the closest product in our e-item database. Recommendation systems (RS) play an important role in e-commerce applications as they help the consumers in choosing the required items within reduced time. The traditional methods of collaborative filtering, fail to capture the visual data associated with the items. Visually-aware recommendation systems are up coming in e-commerce applications that use the visual features of the products rather than the user profiles. Deep learning techniques are used for the classification and prediction in visual recommendation systems.

Keyphrases: deep learning, image retrieval, image similarity, Recommender System

@Booklet{EasyChair:4930,
  author = {Aashutosh Marathe and Maheshwari Patil and Shoeb Shaik and Snehal Waghmare and Kalpana Metre},
  title = {Recommendation System using Content Based Visual Similarity},
  howpublished = {EasyChair Preprint no. 4930},

  year = {EasyChair, 2021}}