Knowing Your Dog Breed:Identifying a Dog Breed with Deep Learning

作     者：Punyanuch Borwarnginn Worapan Kusakunniran Sarattha Karnjanapreechakorn Kittikhun Thongkanchorn Punyanuch Borwarnginn;Worapan Kusakunniran;Sarattha Karnjanapreechakorn;Kittikhun Thongkanchorn

作者机构：Faculty of Information and Communication TechnologyMahidol UniversityNakhon Pathom 73170Thailand 

出 版 物：《International Journal of Automation and computing》 (国际自动化与计算杂志（英文版）)

年 卷 期：2021年第18卷第1期

页      面：45-54页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 0905[农学-畜牧学] 08[工学] 080203[工学-机械设计及理论] 09[农学] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the Royal Golden Jubilee(RGJ)Ph.D.Programme under the Thailand Research Fund(No.PHD/0053/2561) 

主　　题：Computer vision deep learning dog breed classification transfer learning image augmentation 

摘      要：Dog breed identification is essential for many reasons,particularly for understanding individual breeds′conditions,health concerns,interaction behavior,and natural *** paper presents a solution for identifying dog breeds using their images of their *** proposed method applies a deep learning based approach in order to recognize their *** method begins with a transfer learning by retraining existing pretrained convolutional neural networks(CNNs)on the public dog breed ***,the image augmentation with various settings is also applied on the training dataset,in order to improve the classification *** proposed method is evaluated using three different CNNs with various augmentation settings and comprehensive experimental *** proposed model achieves a promising accuracy of 89.92%on the published dataset with 133 dog breeds.