Breakthrough Conventional Based Approach for Dog Breed Classification Using CNN with Transfer Learning

Punyanuch Borwarnginn; Kittikhun Thongkanchorn; Sarattha Kanchanapreechakorn; Worapan Kusakunniran

doi:10.1109/ICITEED.2019.8929955

Breakthrough Conventional Based Approach for Dog Breed Classification Using CNN with Transfer Learning

Punyanuch Borwarnginn
, Kittikhun Thongkanchorn
, Sarattha Kanchanapreechakorn
, Worapan Kusakunniran

Computer Science Academic Group

Mahidol University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

34 Citations (Scopus)

Abstract

Dogs are one of the most common domestic animals. Due to a large number of dogs, there are several issues such as population control, decrease outbreak such as Rabies, vaccination control, and legal ownership. At present, there are over 180 dog breeds. Each dog breed has specific characteristics and health conditions. In order to provide appropriate treatments and training, it is essential to identify individuals and their breeds. The paper presents the classification methods for dog breed classification using two image processing approaches 1) conventional based approaches by Local Binary Pattern (LBP) and Histogram of Oriented Gradient (HOG) 2) the deep learning based approach by using convolutional neural networks (CNN) with transfer learning. The result shows that our retrained CNN model performs better in classifying a dog breeds. It achieves 96.75% accuracy compared with 79.25% using the HOG descriptor.

Original language	English
Title of host publication	2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728140551
DOIs	https://doi.org/10.1109/ICITEED.2019.8929955
Publication status	Published - Oct 2019
Event	11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019 - Pattaya, Thailand Duration: 10 Oct 2019 → 11 Oct 2019

Publication series

Name	2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019

Conference

Conference	11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019
Country/Territory	Thailand
City	Pattaya
Period	10/10/19 → 11/10/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

HOG
LBP
deep learning
dog breed classification
transfer learning

Access to Document

10.1109/ICITEED.2019.8929955

Cite this

Borwarnginn, P., Thongkanchorn, K., Kanchanapreechakorn, S., & Kusakunniran, W. (2019). Breakthrough Conventional Based Approach for Dog Breed Classification Using CNN with Transfer Learning. In 2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019 Article 8929955 (2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICITEED.2019.8929955

Borwarnginn, Punyanuch ; Thongkanchorn, Kittikhun ; Kanchanapreechakorn, Sarattha et al. / Breakthrough Conventional Based Approach for Dog Breed Classification Using CNN with Transfer Learning. 2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019).

@inproceedings{cfbe66a562fe485cb30aeac1390024f6,

title = "Breakthrough Conventional Based Approach for Dog Breed Classification Using CNN with Transfer Learning",

abstract = "Dogs are one of the most common domestic animals. Due to a large number of dogs, there are several issues such as population control, decrease outbreak such as Rabies, vaccination control, and legal ownership. At present, there are over 180 dog breeds. Each dog breed has specific characteristics and health conditions. In order to provide appropriate treatments and training, it is essential to identify individuals and their breeds. The paper presents the classification methods for dog breed classification using two image processing approaches 1) conventional based approaches by Local Binary Pattern (LBP) and Histogram of Oriented Gradient (HOG) 2) the deep learning based approach by using convolutional neural networks (CNN) with transfer learning. The result shows that our retrained CNN model performs better in classifying a dog breeds. It achieves 96.75\% accuracy compared with 79.25\% using the HOG descriptor.",

keywords = "HOG, LBP, deep learning, dog breed classification, transfer learning",

author = "Punyanuch Borwarnginn and Kittikhun Thongkanchorn and Sarattha Kanchanapreechakorn and Worapan Kusakunniran",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019 ; Conference date: 10-10-2019 Through 11-10-2019",

year = "2019",

month = oct,

doi = "10.1109/ICITEED.2019.8929955",

language = "English",

series = "2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019",

}

Borwarnginn, P, Thongkanchorn, K, Kanchanapreechakorn, S & Kusakunniran, W 2019, Breakthrough Conventional Based Approach for Dog Breed Classification Using CNN with Transfer Learning. in 2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019., 8929955, 2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019, Institute of Electrical and Electronics Engineers Inc., 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019, Pattaya, Thailand, 10/10/19. https://doi.org/10.1109/ICITEED.2019.8929955

Breakthrough Conventional Based Approach for Dog Breed Classification Using CNN with Transfer Learning. / Borwarnginn, Punyanuch; Thongkanchorn, Kittikhun; Kanchanapreechakorn, Sarattha et al.
2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8929955 (2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Breakthrough Conventional Based Approach for Dog Breed Classification Using CNN with Transfer Learning

AU - Borwarnginn, Punyanuch

AU - Thongkanchorn, Kittikhun

AU - Kanchanapreechakorn, Sarattha

AU - Kusakunniran, Worapan

PY - 2019/10

Y1 - 2019/10

N2 - Dogs are one of the most common domestic animals. Due to a large number of dogs, there are several issues such as population control, decrease outbreak such as Rabies, vaccination control, and legal ownership. At present, there are over 180 dog breeds. Each dog breed has specific characteristics and health conditions. In order to provide appropriate treatments and training, it is essential to identify individuals and their breeds. The paper presents the classification methods for dog breed classification using two image processing approaches 1) conventional based approaches by Local Binary Pattern (LBP) and Histogram of Oriented Gradient (HOG) 2) the deep learning based approach by using convolutional neural networks (CNN) with transfer learning. The result shows that our retrained CNN model performs better in classifying a dog breeds. It achieves 96.75% accuracy compared with 79.25% using the HOG descriptor.

AB - Dogs are one of the most common domestic animals. Due to a large number of dogs, there are several issues such as population control, decrease outbreak such as Rabies, vaccination control, and legal ownership. At present, there are over 180 dog breeds. Each dog breed has specific characteristics and health conditions. In order to provide appropriate treatments and training, it is essential to identify individuals and their breeds. The paper presents the classification methods for dog breed classification using two image processing approaches 1) conventional based approaches by Local Binary Pattern (LBP) and Histogram of Oriented Gradient (HOG) 2) the deep learning based approach by using convolutional neural networks (CNN) with transfer learning. The result shows that our retrained CNN model performs better in classifying a dog breeds. It achieves 96.75% accuracy compared with 79.25% using the HOG descriptor.

KW - HOG

KW - LBP

KW - deep learning

KW - dog breed classification

KW - transfer learning

UR - https://www.scopus.com/pages/publications/85077970473

U2 - 10.1109/ICITEED.2019.8929955

DO - 10.1109/ICITEED.2019.8929955

M3 - Conference contribution

AN - SCOPUS:85077970473

T3 - 2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019

BT - 2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019

Y2 - 10 October 2019 through 11 October 2019

ER -

Borwarnginn P, Thongkanchorn K, Kanchanapreechakorn S, Kusakunniran W. Breakthrough Conventional Based Approach for Dog Breed Classification Using CNN with Transfer Learning. In 2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8929955. (2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019). doi: 10.1109/ICITEED.2019.8929955

Breakthrough Conventional Based Approach for Dog Breed Classification Using CNN with Transfer Learning

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this