Penerapan Convolutional Neural Network dengan Pre-Trained Model Xception untuk Meningkatkan Akurasi dalam Mengidentifikasi Jenis Ras Kucing

Abraham Imanuel, Djoni Haryadi Setiabudi

Abstract


Raising pets is a common thing that humans often do. Cats are one of the domestic pets that are fancied by humans. But, raising a cat is not an easy task. This is because every cat’s breed has its own characteristics that will affect its type of raising. Because of that, there is a need for a system that can identify a cat’s breed to help someone in deciding which type of cat is suitable for him/her. In the past, there was also research about cat’s breed detection using SSD Mobilenet_v1 FPN method, but the accuracy was not high enough, which was 81.74%. This thesis will be done with the implementation of transfer learning method on Pre-Trained Convolutional Neural Network Xception, which is a CNN Model that is inspired by CNN Model Inception. CNN Model Xception is an Inception Model that replaces the use of Inception modules with depth wise separable convolutions. CNN Model Xception is used in this thesis with the purpose of increasing the accuracy of cat’s breed detection. Output of the system shows that the highest accuracy that could be made in detecting cat’s breeds on The Oxford-IIIT Pet Dataset is 89.58% or 0.8958. Compared to SSD Mobilenet_v1 FPN method, which accuracy was 81.74%, implementing Xception method gives an increase in the accuracy for 7.84%. Other than that, it is also found that the dataset quality has an impact on model’s accuracy.

Keywords


Cat Breed; Convolutional Neural Network; Pre-Trained Model; Xception; Transfer Learning; Depthwise Separable Convolutions.

Full Text:

PDF

References


China Daily. 2009, November 3. Meet Helen and Aphrodite,

Cyprus’s Indigenous Cats. Retrieved August 31, 2021 from :

http://www.chinadaily.com.cn/life/2009-11/03/content_8904

htm.

Chollet, F. 2017, April 4. Xception: Deep Learning with

Depthwise Separable Convolutions. Retrieved December 15,

from https://arxiv.org/pdf/1610.02357.pdf.

DOI:10.1109/CVPR.2017.195

Dike, H. U., Zhou, Y., Deveerasetty, K., K. and Wu, Q.

Unsupervised Learning Based On Artificial Neural

Network: A Review. 2018 IEEE International Conference on

Cyborg and Bionic Systems (CBS), 2018, pp. 322-327, DOI:

1109/CBS.2018.8612259.

Jacobberger, P. Coats and Colors: How does the Description

Works? Retrieved October 9, 2021 from : https://cfa.org/

coat-and-color-descriptions/.

Mariani, L. 2014. Aplikasi Pendeteksian Ras Kucing Dengan

Mendeteksi Wajah Kucing Dengan Metode Viola Jones

Berbasis Android. Retrieved August 31, 2021 from

https://elib.unikom.ac.id/gdl.php?mod=browse&op=read&id

=jbptunikompp-gdl-lenimarian-35067.

Nugroho, K., S. 2019, November 13. Confusion Matrix

untuk Evaluasi Model pada Supervised Learning. Retrieved

August 31, 2021 from : https://medium.com/@ksnug

roho/confusion-matrix-untuk-evaluasi-model-pada-unsuperv

ised-machine-learning-bc4b1ae9ae3f.

Oktaviana, P.A., Dwinata, M. & Oka, I.B.M. 2014, August

Prevalensi Infeksi Cacing Ancylostoma Spp Pada Kucing

Lokal (Felis catus) di Kota Denpasar. Buletin Veteriner

Udayana. ISSN: 2477-2712. Retrieved August 31, 2021

from: https://ojs.unud.ac.id/index.php/buletinvet/article/view

/10628.

Pangestu, M.A. & Bunyamin, H. 2018, August 2. Analisis

Performa dan Pengembangan Sistem Deteksi Ras Anjing

pada Gambar dengan Menggunakan Pre-Trained CNN

Model. Jurnal Teknik Informatika dan Sistem Informasi, 4,

-344.

Pickrell, J. 2004, April 9. Oldest Known Pet Cat?

,500-Year-Old Burial Found on Cyprus. Retrieved August

, 2021 from: https://www.nationalgeographic.com

/animals/article/oldest-known-pet-cat-9500-year-old-burial

-found-on-cyprus.

Rahmiati, D.U. & Pribadi, E.S. 2014, October 5. Tingkat

Pendidikan dan Status Ekonomi Pemilik Hewan Kesayangan

dalam Hal Pengetahuan dan Penerapan Kesejahteraan

Hewan. J Vet. 15(3): 386-394. Retrieved 31 August, 2021

from:https://ojs.unud.ac.id/index.php/jvet/article/view/10041

Ramdan, A. et al. 2020. Transfer Learning and Fine-Tuning

for Deep Learning-Based Tea Diseases Detection on Small

Datasets. 2020 International Conference on Radar, Antenna,

Microwave, Electronics, and Telecommunications

(ICRAMET), pp. 206-211, DOI:

1109/ICRAMET51080.2020.9298575.

Thornton, C. 2018, January 16. The Ragdoll Cat — All

About This Fascinating Cat Breed. Retrieved August 31,

from: https://www.catster.com/cats-101/about-the

-ragdoll-cat.

Zhang, X., Yang, L., & Sinnott, R. 2019, March 25. A

Mobile Application for Cat Detection and Breed

Recognition Based on Deep Learning. 2019 IEEE 1st

International Workshop on Artificial Intelligence for Mobile

(AI4Mobile). DOI:10.1109/ai4mobile.2019.8672684.

Zhuang, F. et al. 2021. A Comprehensive Survey on Transfer

Learning. Proceedings of the IEEE, vol. 109, no. 1, pp.

-76, Jan. 2021, DOI: 10.1109/JPROC.2020.3004555.


Refbacks

  • There are currently no refbacks.


Jurnal telah terindeks oleh :