Identifikasi Foto Fashion Dengan Menggunakan Convolutional Neural Network (CNN)

Green Arther Sandag, Jacquline Waworundeng

Abstract


Perkembangan teknologi sekarang ini berdampak pada banyak hal, salah satunya ialah pada bidang fashion. Penggunaan Artificial Intelligence dan juga deep learning dapat dimanfaatkan dalam bidang fashion, salah satu contohnya adalah pengenalan objek clothing. Pada penelitian ini, peneliti mengidentifikasi mode pakaian dengan menggunakan metode Convolutional Neural Network (CNN), dan library Tensorflow, serta menggunakan Fashion MNIST dataset untuk menguji kemampuan CNN model. Hasil yang didapatkan saat pengujian dengan menggunakan berbagai convolutional layer sekuensial yang kompleks, didapati dua hasil yang sedikit berbeda. Pengujian pada model pertama, terjadi overfitting, sehingga menghasilkan akurasi sebesar 91%. Pada pengujian kedua, dengan penambahan Dropout layers, menghasilkan akurasi yang lebih baik, yaitu sebesar 93%. Melihat dari hasil yang didapatkan, penggunaan CNN dalam mengidentifikasi mode pakaian cukup sesuai karena dapat mencapai akurasi hingga 93%.

 

 

Kata kunci — Deep Learning, Pengenalan objek , Convolutional Neural Network (CNN), Tensorflow, Fashion MNIST


Full Text:

PDF

References


Y. Seo and K.-S. Shin, “Hierarchical Convolutional Neural Networks for Fashion Image Classification,” Expert Systems With Applications, vol. 116, pp. 328–339, Feb. 2019, doi: 10.1016/j.eswa.2018.09.022.

M. Kayed, A. Anter, and H. Mohamed, “Classification of Garments from Fashion MNIST Dataset Using CNN LeNet-5 Architecture,” p. 6.

Y. Zhang, “Evaluation of CNN Models with Fashion MNIST Data,” p. 42, 2019.

K. V. Greeshma and K. Sreekumar, “Fashion-MNIST Classification Based on HOG Feature Descriptor Using SVM,” International Journal of Innovative Technology and Exploring Engineering (IJITEE), vol. 8, no. 5, pp. 960–962, 2019.

M. S. Bhatnagar, M. D. Ghosal, and D. M. H. Kolekar, “Classification of Fashion Article Images Using Convolutional Neural Networks,” p. 6, 2017.

L. Donati, E. Iotti, G. Mordonini, and A. Prati, “Fashion Product Classification through Deep Learning and Computer Vision,” p. 22, 2019.

M. Xu, “Segmentation of lung parenchyma in CT images using CNN trained with the clustering algorithm generated dataset,” p. 21, 2019.

S. S. Kadam, A. C. Adamuthe, and A. B. Patil, “CNN Model for Image Classification on MNIST and Fashion-MNIST Dataset,” Journal of Scientific Research, vol. 64, no. 2, p. 11, 2020.

H. Xiao, K. Rasul, and R. Vollgraf, “Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms,” arXiv:1708.07747 [cs, stat], Sep. 2017, Accessed: Nov. 18, 2020. [Online]. Available: http://arxiv.org/abs/1708.07747.

S. Priyowidodo, “KLASIFIKASI GAMBAR DATASET FASHION-MNIST MENGGUNAKAN DEEP CONVOLUTIONAL NEURAL NETWORK,” vol. 7, no. 1, p. 5, 2019.

A. F. M. Agarap, “Deep Learning using Rectified Linear Units (ReLU),” p. 8, Mar. 2018.

A. Prajapati, A. Kaushik, P. Gupta, S. Sharma, and S. Jain, “Fashion Product Image Classification Using Neural Network,” vol. 3, no. 4, p. 3.

C. Geier, “Training on test data: Removing near duplicates in Fashion-MNIST,” arXiv:1906.08255 [cs, stat], Jun. 2019, Accessed: Nov. 29, 2020. [Online]. Available: http://arxiv.org/abs/1906.08255.

S. Shubathra, P. Kalaivaani, and S. Santhoshkumar, “Clothing Image Recognition Based on Multiple Features Using Deep Neural Networks,” p. 7, 2020.

F. K. Celsia, G. A. Sandag, “Implementasi Deep Learning pada Pengenalan Angka dalam Sign Language,” Jurnal Ilmiah Sistem Informasi dan Teknik informatika (SISFOTENIKA). vol 11, no. 2. p 124-126. Juli. 2021.




DOI: http://dx.doi.org/10.31154/cogito.v7i2.340.305-314

Refbacks

  • There are currently no refbacks.


CogITo Smart Journal
A publication of Fakultas Ilmu Komputer, Universitas Klabat
In partnership with Coris and IndoCEISS
Phone: +62 (431) 891035
email: editorial.cogito@unklab.ac.id | web: http://cogito.unklab.ac.id/index.php/cogito
 
Free counters!
View CogITo Smart Journal Stats

CogITo Smart Journal is indexed by:
  DOAJ    SINTA     Indonesia OneSearch by Perpusnas    Crossref    Google Scholar      Base Search PKP Index    neliti    EBSCO Information Science    mendeley          scilit    road    worldcat    DRJI    OpenAIREplus    copac    Gent University Library Stanford Library    Harvard Library    Leiden University Libraries    The University of Sheffield    Boston University Library    University of Manchester    University of Oxford    CORE    Livivo
 


CogITo Smart Journal is licensed under a Creative Commons Attribution 4.0 International License.