Clothing classification using Vision Transformer and Efficient-Net and CNN

Project Code :TCMAPY2361

Objective

The main objective of this project is to build an efficient clothing classification system using deep learning models like EfficientNet, Vision Transformer, and CNN. The system aims to classify various clothing items such as dresses, hats, pants, shirts, and shoes into predefined categories. By leveraging the power of advanced models, the project seeks to achieve high classification accuracy, improving the speed and reliability of clothing item detection in various applications like online shopping platforms and inventory management systems.

Abstract

Clothing classification plays an important role in fashion and retail industries, facilitating automatic tagging, recommendation, and customer experience optimization. This project explores the application of deep learning methods, including EfficientNet, Vision Transformer, and Convolutional Neural Networks (CNN), to classify clothing items from a diverse set of categories such as dresses, hats, pants, shirts, and shoes. The dataset used for this project is sourced from Kaggle and consists of a large collection of labeled clothing images. The classification model utilizes various feature extraction and training techniques to achieve high accuracy and robustness. The system is designed to provide accurate clothing item classification that could benefit various applications, including online shopping, inventory management, and image-based fashion recommendation systems.

Keywords: Clothing classification, deep learning, EfficientNet, CNN, Vision Transformer, Kaggle dataset, fashion recommendation, image classification

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.