A federated approach for fine-grained classification of fashion apparel
As online retail services proliferate and are pervasive in modern lives, applications for classifying fashion apparel features from image data are becoming more indispensable. Online retailers, from leading companies to start-ups, can leverage such applications in order to increase profit margin and...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2021-12-01
|
Series: | Machine Learning with Applications |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666827021000591 |
id |
doaj-27e370b0ab3b4c6ab9a0d83ebfd3a7db |
---|---|
record_format |
Article |
spelling |
doaj-27e370b0ab3b4c6ab9a0d83ebfd3a7db2021-08-10T04:05:20ZengElsevierMachine Learning with Applications2666-82702021-12-016100118A federated approach for fine-grained classification of fashion apparelTejaswini Mallavarapu0Luke Cranfill1Eun Hye Kim2Reza M. Parizi3John Morris4Junggab Son5Information and Intelligent Security (IIS) Lab, Kennesaw State University, Marietta, GA 30060, USA; Analytics and Data Science Institute, Kennesaw State University, Marietta, GA 30060, USAInformation and Intelligent Security (IIS) Lab, Kennesaw State University, Marietta, GA 30060, USAInformation and Intelligent Security (IIS) Lab, Kennesaw State University, Marietta, GA 30060, USADecentralized Science Lab, Kennesaw State University, Marietta, GA 30060, USAOracle, Retail Global Business Unit, Atlanta, GA, USAInformation and Intelligent Security (IIS) Lab, Kennesaw State University, Marietta, GA 30060, USA; Corresponding author.As online retail services proliferate and are pervasive in modern lives, applications for classifying fashion apparel features from image data are becoming more indispensable. Online retailers, from leading companies to start-ups, can leverage such applications in order to increase profit margin and enhance the consumer experience. Many notable schemes have been proposed to classify fashion items, however, the majority of such schemes have focused upon classifying basic-level categories, such as T-shirts, pants, skirts, shoes, bags, and so forth. In contrast to most prior efforts, this paper aims to enable an in-depth classification of fashion item attributes within the same category. Beginning with a single dress, we seek to classify the type of dress hem, the hem length, and the sleeve length. The proposed scheme is comprised of three major stages: (a) localization of a target item from an input image using semantic segmentation, (b) detection of human key points (e.g., point of shoulder) using a pre-trained CNN and a bounding box, and (c) three-phase classification of the attributes using a combination of algorithmic approaches and deep neural networks. The experimental results demonstrate that the proposed scheme is highly effective, with all categories having average precision of above 93.02%, and outperforms existing Convolutional Neural Networks (CNNs)-based schemes.http://www.sciencedirect.com/science/article/pii/S2666827021000591Apparel attributesApparel classificationFine-grained classificationHuman keypoints detection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Tejaswini Mallavarapu Luke Cranfill Eun Hye Kim Reza M. Parizi John Morris Junggab Son |
spellingShingle |
Tejaswini Mallavarapu Luke Cranfill Eun Hye Kim Reza M. Parizi John Morris Junggab Son A federated approach for fine-grained classification of fashion apparel Machine Learning with Applications Apparel attributes Apparel classification Fine-grained classification Human keypoints detection |
author_facet |
Tejaswini Mallavarapu Luke Cranfill Eun Hye Kim Reza M. Parizi John Morris Junggab Son |
author_sort |
Tejaswini Mallavarapu |
title |
A federated approach for fine-grained classification of fashion apparel |
title_short |
A federated approach for fine-grained classification of fashion apparel |
title_full |
A federated approach for fine-grained classification of fashion apparel |
title_fullStr |
A federated approach for fine-grained classification of fashion apparel |
title_full_unstemmed |
A federated approach for fine-grained classification of fashion apparel |
title_sort |
federated approach for fine-grained classification of fashion apparel |
publisher |
Elsevier |
series |
Machine Learning with Applications |
issn |
2666-8270 |
publishDate |
2021-12-01 |
description |
As online retail services proliferate and are pervasive in modern lives, applications for classifying fashion apparel features from image data are becoming more indispensable. Online retailers, from leading companies to start-ups, can leverage such applications in order to increase profit margin and enhance the consumer experience. Many notable schemes have been proposed to classify fashion items, however, the majority of such schemes have focused upon classifying basic-level categories, such as T-shirts, pants, skirts, shoes, bags, and so forth. In contrast to most prior efforts, this paper aims to enable an in-depth classification of fashion item attributes within the same category. Beginning with a single dress, we seek to classify the type of dress hem, the hem length, and the sleeve length. The proposed scheme is comprised of three major stages: (a) localization of a target item from an input image using semantic segmentation, (b) detection of human key points (e.g., point of shoulder) using a pre-trained CNN and a bounding box, and (c) three-phase classification of the attributes using a combination of algorithmic approaches and deep neural networks. The experimental results demonstrate that the proposed scheme is highly effective, with all categories having average precision of above 93.02%, and outperforms existing Convolutional Neural Networks (CNNs)-based schemes. |
topic |
Apparel attributes Apparel classification Fine-grained classification Human keypoints detection |
url |
http://www.sciencedirect.com/science/article/pii/S2666827021000591 |
work_keys_str_mv |
AT tejaswinimallavarapu afederatedapproachforfinegrainedclassificationoffashionapparel AT lukecranfill afederatedapproachforfinegrainedclassificationoffashionapparel AT eunhyekim afederatedapproachforfinegrainedclassificationoffashionapparel AT rezamparizi afederatedapproachforfinegrainedclassificationoffashionapparel AT johnmorris afederatedapproachforfinegrainedclassificationoffashionapparel AT junggabson afederatedapproachforfinegrainedclassificationoffashionapparel AT tejaswinimallavarapu federatedapproachforfinegrainedclassificationoffashionapparel AT lukecranfill federatedapproachforfinegrainedclassificationoffashionapparel AT eunhyekim federatedapproachforfinegrainedclassificationoffashionapparel AT rezamparizi federatedapproachforfinegrainedclassificationoffashionapparel AT johnmorris federatedapproachforfinegrainedclassificationoffashionapparel AT junggabson federatedapproachforfinegrainedclassificationoffashionapparel |
_version_ |
1721212965160484864 |