Automatic classification of Breeds of Dog using Convolutional Neural Network
Dog is a mammal that has been a friend of man for ages, it is naturally a domestic animal with a high level of phenotype differences in behaviour and morphology. Breeding and crossbreeding activities have increased the number of dog breeds globally, thereby resulting in dogs with inter breed simila...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Faculty of Engineering and Technology
2023-09-01
|
Series: | Nigerian Journal of Technological Development |
Subjects: | |
Online Access: | https://journal.njtd.com.ng/index.php/njtd/article/view/1485 |
_version_ | 1797678050710650880 |
---|---|
author | P. O. Adejumobi I. O. Adejumobi O. A. Adebisi S. O. Ayanlade I. I. Adeaga |
author_facet | P. O. Adejumobi I. O. Adejumobi O. A. Adebisi S. O. Ayanlade I. I. Adeaga |
author_sort | P. O. Adejumobi |
collection | DOAJ |
description |
Dog is a mammal that has been a friend of man for ages, it is naturally a domestic animal with a high level of phenotype differences in behaviour and morphology. Breeding and crossbreeding activities have increased the number of dog breeds globally, thereby resulting in dogs with inter breed similarities and intra breed differences thereby creating a difficulty in their classification. The American Kennel Club (AKC) classified breeds of dog into groups based on characteristic, purpose, behaviuor and uses in order to optimize the potentials in the breeds. However, most people find it difficult to identify and classify the dog breed groups. Existing works did not consider the automatic grouping of dog breeds. Hence, there is need for automatic techniques to classify dog breeds into groups with improved accuracy. This work used the concept of Convolutional Neural Network (CNN) to develop a model that will automatically classify dog breeds into group based on the American Kennel Club standard using the Stanford’s dog dataset. The developed model achieved 92.2% accuracy, 80.0% sensitivity, 95.3% specificity and 93.4% area under curve (AUC). The model’s performance is excellent compared to existing works that used the same dataset. The experimental result was validated with two classic CNN models (ResNet-50 and SqueezeNet) using the same parameters.
|
first_indexed | 2024-03-11T22:53:49Z |
format | Article |
id | doaj.art-c7d6f844327244639d4b524b8b7b2816 |
institution | Directory Open Access Journal |
issn | 2437-2110 |
language | English |
last_indexed | 2024-03-11T22:53:49Z |
publishDate | 2023-09-01 |
publisher | Faculty of Engineering and Technology |
record_format | Article |
series | Nigerian Journal of Technological Development |
spelling | doaj.art-c7d6f844327244639d4b524b8b7b28162023-09-21T21:28:38ZengFaculty of Engineering and TechnologyNigerian Journal of Technological Development2437-21102023-09-01203Automatic classification of Breeds of Dog using Convolutional Neural NetworkP. O. Adejumobi0I. O. Adejumobi1O. A. Adebisi2S. O. Ayanlade I. I. Adeaga3Engr.Ladoke Akintola University, OgbomosoLadoke Akintola University OgbomosoThe Polytechnic Ibadan Dog is a mammal that has been a friend of man for ages, it is naturally a domestic animal with a high level of phenotype differences in behaviour and morphology. Breeding and crossbreeding activities have increased the number of dog breeds globally, thereby resulting in dogs with inter breed similarities and intra breed differences thereby creating a difficulty in their classification. The American Kennel Club (AKC) classified breeds of dog into groups based on characteristic, purpose, behaviuor and uses in order to optimize the potentials in the breeds. However, most people find it difficult to identify and classify the dog breed groups. Existing works did not consider the automatic grouping of dog breeds. Hence, there is need for automatic techniques to classify dog breeds into groups with improved accuracy. This work used the concept of Convolutional Neural Network (CNN) to develop a model that will automatically classify dog breeds into group based on the American Kennel Club standard using the Stanford’s dog dataset. The developed model achieved 92.2% accuracy, 80.0% sensitivity, 95.3% specificity and 93.4% area under curve (AUC). The model’s performance is excellent compared to existing works that used the same dataset. The experimental result was validated with two classic CNN models (ResNet-50 and SqueezeNet) using the same parameters. https://journal.njtd.com.ng/index.php/njtd/article/view/1485stanford's dog dataset, convolutional neural networkdeep learning |
spellingShingle | P. O. Adejumobi I. O. Adejumobi O. A. Adebisi S. O. Ayanlade I. I. Adeaga Automatic classification of Breeds of Dog using Convolutional Neural Network Nigerian Journal of Technological Development stanford's dog dataset, convolutional neural network deep learning |
title | Automatic classification of Breeds of Dog using Convolutional Neural Network |
title_full | Automatic classification of Breeds of Dog using Convolutional Neural Network |
title_fullStr | Automatic classification of Breeds of Dog using Convolutional Neural Network |
title_full_unstemmed | Automatic classification of Breeds of Dog using Convolutional Neural Network |
title_short | Automatic classification of Breeds of Dog using Convolutional Neural Network |
title_sort | automatic classification of breeds of dog using convolutional neural network |
topic | stanford's dog dataset, convolutional neural network deep learning |
url | https://journal.njtd.com.ng/index.php/njtd/article/view/1485 |
work_keys_str_mv | AT poadejumobi automaticclassificationofbreedsofdogusingconvolutionalneuralnetwork AT ioadejumobi automaticclassificationofbreedsofdogusingconvolutionalneuralnetwork AT oaadebisi automaticclassificationofbreedsofdogusingconvolutionalneuralnetwork AT soayanlade automaticclassificationofbreedsofdogusingconvolutionalneuralnetwork AT iiadeaga automaticclassificationofbreedsofdogusingconvolutionalneuralnetwork |