Accesso libero

Analysis of Clothing Image Classification Models: A Comparison Study between Traditional Machine Learning and Deep Learning Models

Jun Xu

Jun Xu

Tiangong UniversityTianjin, China
Profilo Orcid
Cerca questo autore su
Sciendo|Google Scholar
Xu, Jun
, 
Yumeng Wei

Yumeng Wei

Tiangong UniversityTianjin, China
Profilo Orcid
Cerca questo autore su
Sciendo|Google Scholar
Wei, Yumeng
, 
Aichun Wang

Aichun Wang

Tiangong UniversityTianjin, China
Cerca questo autore su
Sciendo|Google Scholar
Wang, Aichun
, 
Heng Zhao

Heng Zhao

Shenzhen Technology UniversityShenzhen, China
Profilo Orcid
Cerca questo autore su
Sciendo|Google Scholar
Zhao, Heng
 e 
Damien Lefloch

Damien Lefloch

Tiangong UniversityTianjin, China
Profilo Orcid
Cerca questo autore su
Sciendo|Google Scholar
Lefloch, Damien
  
22 dic 2022
Analysis of Clothing Image Classification Models: A Comparison Study between Traditional Machine Learning and Deep Learning Models's Cover Image
INFORMAZIONI SU QUESTO ARTICOLO
Articolo precedente
Articolo Successivo
Cita
Scarica la copertina
Categoria dell'articolo: Research Article
Pubblicato online: 22 dic 2022
Pagine: 66 - 78
DOI: https://doi.org/10.2478/ftee-2022-0046
Parole chiave
© 2022 Jun Xu et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Fig. 1

Research object and methodology
Research object and methodology

Fig. 2

Flow chart of clothing image classification
Flow chart of clothing image classification

Fig. 3

Schematic diagram of HOG+SVM algorithm
Schematic diagram of HOG+SVM algorithm

Fig. 4

Architecture of a simple NN
Architecture of a simple NN

Fig. 5

Architecture of the CNN
Architecture of the CNN

Fig. 6

Architecture of small VGG
Architecture of small VGG

Fig. 7

Experimental flow chart
Experimental flow chart

Fig. 8

Examples and categories of the Fashion-MNIST dataset
Examples and categories of the Fashion-MNIST dataset

Fig. 9

Accuracy comparison of HOG+SVM, NN, and CNN.
Accuracy comparison of HOG+SVM, NN, and CNN.

Fig. 10

Example images of the Fashion144k dataset
Example images of the Fashion144k dataset

Fig. 11

Example images of the SmallV1 dataset
Example images of the SmallV1 dataset

Fig. 12

Recognition accuracy of HOG+SVM and Small VGG for the SmallV1 dataset
Recognition accuracy of HOG+SVM and Small VGG for the SmallV1 dataset

Fig. 13

Recognition accuracy of Small VGG network models in different datasets
Recognition accuracy of Small VGG network models in different datasets

Fig. 14

Recognition accuracy of the GhostNet model for different datasets
Recognition accuracy of the GhostNet model for different datasets

Fig. 15

Accuracy of Small VGG and GhostNet for different numbers of datasets
Accuracy of Small VGG and GhostNet for different numbers of datasets

Fashion-MNIST dataset label description

Description T-shirt/top Trouser Pullover Dress Notes
Label 0 1 2 3 4
Description Sandal Shirt Sneaker Bag Ankle boot
Label 5 6 7 8 9

Highest accuracy comparison of different models

Name Highest Accuracy
ML (rbf_4x4) 91.3%
CNN 89.7%
ML (Linear_4x4) 88.9%
NN 87.7%
ML (rbf_8x8) 86.7%
ML (Linear_8x8) 83.1%
Lingua:
Inglese
Frequenza di pubblicazione:
Volume Open
Argomenti della rivista:
Economia e business, Business management, Informatica del business, Process Management, Chimica idustriale, Cellulosa, carta e tessuti, Scienza e tecnologia dei polimeri, Scienze materiali, Biomateriali e materiali naturali
Feed RSS della rivista