DETECTION AND CLASSIFICATION OF SEASON CLOTHES USING ML ON THE EDGE
Loading...
Date
2024-04-19
Authors
Sakenkyzy, Alua
Yeraliyeva, Nazerke
Bekubayev, Arsen
Sovet, Sanzhar
Journal Title
Journal ISSN
Volume Title
Publisher
Nazarbayev University School of Engineering and Digital Sciences
Abstract
The creation of a machine learning (ML) model for the automatic identification of
different types of seasonal clothes was the main goal of our research. The objective was to
categorize into four main groups: winter clothes, trousers, long-sleeve, and short-sleeve
items. Our goal was to facilitate the precise and efficient identification of different kinds of
clothing products by utilizing Convolutional Neural Network (CNN) algorithms about their
seasonal properties. We collected a dataset of over 1000 photos that represented the four-goal
categories to train and evaluate our model. Carefully tagged images were used to enable
supervised learning. The model gained the ability to recognize patterns and characteristics
typical of various seasonal clothes through a process of training and validation, facilitating
precise categorization. After a long training and validation process, our CNN model
performed admirably in the classification of seasonal cloth. The classification accuracy of the
model was higher than 80%. This high accuracy demonstrates the effectiveness of our
method and its potential for useful use in real-world settings.
Description
Keywords
Type of access: Restricted, Machine Learning, OpenMV, Classification, Seasonal clothes, Neural Network
Citation
Bekubayev, A., Sovet, S., Sakenkyzy, A., & Yeraliyeva, N. (2024). Detection and Classification of Season Clothes using ML on the Edge. Nazarbayev University School of Engineering and Digital Sciences