Smart Clothing Recommendation System with Deep Learning
- 1 October 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Abstract
Recommendation systems based on machine learning are very important both customers and sellers in our daily life. Many recommendation systems need user’s previous shopping activities and digital footprints to make best recommendation purpose for next item shopping. In this study, we develop a cloth recommendation system with using only single photo of user with scalable embedded system. This study lead to important results and give new opportunities for clothing companies and advertisements. In this study, we show that how our system recommends a cloth options without user’s previous shopping act data with embedded system and machine learning. In order to recommend a cloth, we develop two inception based convolutional neural networks as prediction part and one feed forward neural network as recommender. In this study, we reach to 98% accuracy on color prediction, 86% accuracy on gender and cloth’s pattern predictions and 75% accuracy on clothing recommendation.Keywords
This publication has 9 references indexed in Scilit:
- Research on Clothing Image Classification by Convolutional Neural Networks2018
- Digital Data Forgetting: A Machine Learning Approach2018
- Rethinking the Inception Architecture for Computer Vision2016
- On the posibility of using difference of Gaussians for texture clasification2012
- Describing Clothing by Semantic Attributes2012
- Fast training and selection of Haar features using statistics in boosting-based face detection2007
- An extended set of Haar-like features for rapid object detection2003
- Progressive switching median filter for the removal of impulse noise from highly corrupted imagesIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1999
- Evaluation of convolutional neural networks for visual recognitionIEEE Transactions on Neural Networks, 1998