Research note: Application of convolutional neural networks for feather classification in chickens

Feather color plays a crucial role in distinguishing various poultry breeds. However, the reliability of conventional manual classification methods is debated due to the intricate nature of feather color traits. To address this issue, we applied Convolutional Neural Networks (CNN) to extract the fea...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiajia Niu, Tong Li, Kunlong Qi, Yang Liu, Haixuan Deng, Yujia Hu, Dan Xu, Liuting Wu, Felix Kwame Amevor, Yingjie Wang, Gang Shu, Xiaoling Zhao
Format: Article
Language:English
Published: Elsevier 2025-11-01
Series:Poultry Science
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0032579125004961
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849239322284261376
author Jiajia Niu
Tong Li
Kunlong Qi
Yang Liu
Haixuan Deng
Yujia Hu
Dan Xu
Liuting Wu
Felix Kwame Amevor
Yingjie Wang
Gang Shu
Xiaoling Zhao
author_facet Jiajia Niu
Tong Li
Kunlong Qi
Yang Liu
Haixuan Deng
Yujia Hu
Dan Xu
Liuting Wu
Felix Kwame Amevor
Yingjie Wang
Gang Shu
Xiaoling Zhao
author_sort Jiajia Niu
collection DOAJ
description Feather color plays a crucial role in distinguishing various poultry breeds. However, the reliability of conventional manual classification methods is debated due to the intricate nature of feather color traits. To address this issue, we applied Convolutional Neural Networks (CNN) to extract the feather texture features of 300 images each of Golden Meihua (GM) and Silver Meihua (SM) feathers. The nonlinear features were then learned through an MLP layer and activation functions to complete the classification of GM and SM. Finally, we successfully developed a method automating the identification of feather texture features, achieving a recognition model accuracy of 93.71 % after 5-fold cross-validation. This research improves the precision and effectiveness of feather color selection, offering valuable insights into the systematic classification of feather colors in diverse poultry species.
format Article
id doaj-art-ae85f326564f4ece96c270bf1c8a7021
institution Kabale University
issn 0032-5791
language English
publishDate 2025-11-01
publisher Elsevier
record_format Article
series Poultry Science
spelling doaj-art-ae85f326564f4ece96c270bf1c8a70212025-08-20T04:01:02ZengElsevierPoultry Science0032-57912025-11-011041110525410.1016/j.psj.2025.105254Research note: Application of convolutional neural networks for feather classification in chickensJiajia Niu0Tong Li1Kunlong Qi2Yang Liu3Haixuan Deng4Yujia Hu5Dan Xu6Liuting Wu7Felix Kwame Amevor8Yingjie Wang9Gang Shu10Xiaoling Zhao11State Key Laboratory of Swine and Poultry Breeding Industry, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Key Laboratory of Livestock and Poultry Multi-omics, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Farm Animal Genetic Resources Exploration and Innovation Key Laboratory of Sichuan Province, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR ChinaState Key Laboratory of Swine and Poultry Breeding Industry, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Key Laboratory of Livestock and Poultry Multi-omics, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Farm Animal Genetic Resources Exploration and Innovation Key Laboratory of Sichuan Province, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR ChinaState Key Laboratory of Swine and Poultry Breeding Industry, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Key Laboratory of Livestock and Poultry Multi-omics, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Farm Animal Genetic Resources Exploration and Innovation Key Laboratory of Sichuan Province, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR ChinaState Key Laboratory of Swine and Poultry Breeding Industry, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Key Laboratory of Livestock and Poultry Multi-omics, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Farm Animal Genetic Resources Exploration and Innovation Key Laboratory of Sichuan Province, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR ChinaState Key Laboratory of Swine and Poultry Breeding Industry, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Key Laboratory of Livestock and Poultry Multi-omics, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Farm Animal Genetic Resources Exploration and Innovation Key Laboratory of Sichuan Province, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR ChinaState Key Laboratory of Swine and Poultry Breeding Industry, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Key Laboratory of Livestock and Poultry Multi-omics, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Farm Animal Genetic Resources Exploration and Innovation Key Laboratory of Sichuan Province, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR ChinaState Key Laboratory of Swine and Poultry Breeding Industry, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Key Laboratory of Livestock and Poultry Multi-omics, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Farm Animal Genetic Resources Exploration and Innovation Key Laboratory of Sichuan Province, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR ChinaState Key Laboratory of Swine and Poultry Breeding Industry, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Key Laboratory of Livestock and Poultry Multi-omics, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Farm Animal Genetic Resources Exploration and Innovation Key Laboratory of Sichuan Province, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR ChinaState Key Laboratory of Swine and Poultry Breeding Industry, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Key Laboratory of Livestock and Poultry Multi-omics, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Farm Animal Genetic Resources Exploration and Innovation Key Laboratory of Sichuan Province, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR ChinaState Key Laboratory of Swine and Poultry Breeding Industry, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Key Laboratory of Livestock and Poultry Multi-omics, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Farm Animal Genetic Resources Exploration and Innovation Key Laboratory of Sichuan Province, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR ChinaDepartment of Basic Veterinary Medicine, Sichuan Agricultural University, Chengdu, Sichuan 611130, PR ChinaState Key Laboratory of Swine and Poultry Breeding Industry, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Key Laboratory of Livestock and Poultry Multi-omics, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Farm Animal Genetic Resources Exploration and Innovation Key Laboratory of Sichuan Province, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China; Correspondence author: Xiaoling Zhao, Key Laboratory of Livestock and Poultry Multi-omics, College of Animal Science and Technology, Sichuan Agricultural University, Chengdu, Sichuan, PR China, Zipcode: 611134.Feather color plays a crucial role in distinguishing various poultry breeds. However, the reliability of conventional manual classification methods is debated due to the intricate nature of feather color traits. To address this issue, we applied Convolutional Neural Networks (CNN) to extract the feather texture features of 300 images each of Golden Meihua (GM) and Silver Meihua (SM) feathers. The nonlinear features were then learned through an MLP layer and activation functions to complete the classification of GM and SM. Finally, we successfully developed a method automating the identification of feather texture features, achieving a recognition model accuracy of 93.71 % after 5-fold cross-validation. This research improves the precision and effectiveness of feather color selection, offering valuable insights into the systematic classification of feather colors in diverse poultry species.http://www.sciencedirect.com/science/article/pii/S0032579125004961Feather colorConvolutional Neural Networkchickenbreedingclassification
spellingShingle Jiajia Niu
Tong Li
Kunlong Qi
Yang Liu
Haixuan Deng
Yujia Hu
Dan Xu
Liuting Wu
Felix Kwame Amevor
Yingjie Wang
Gang Shu
Xiaoling Zhao
Research note: Application of convolutional neural networks for feather classification in chickens
Poultry Science
Feather color
Convolutional Neural Network
chicken
breeding
classification
title Research note: Application of convolutional neural networks for feather classification in chickens
title_full Research note: Application of convolutional neural networks for feather classification in chickens
title_fullStr Research note: Application of convolutional neural networks for feather classification in chickens
title_full_unstemmed Research note: Application of convolutional neural networks for feather classification in chickens
title_short Research note: Application of convolutional neural networks for feather classification in chickens
title_sort research note application of convolutional neural networks for feather classification in chickens
topic Feather color
Convolutional Neural Network
chicken
breeding
classification
url http://www.sciencedirect.com/science/article/pii/S0032579125004961
work_keys_str_mv AT jiajianiu researchnoteapplicationofconvolutionalneuralnetworksforfeatherclassificationinchickens
AT tongli researchnoteapplicationofconvolutionalneuralnetworksforfeatherclassificationinchickens
AT kunlongqi researchnoteapplicationofconvolutionalneuralnetworksforfeatherclassificationinchickens
AT yangliu researchnoteapplicationofconvolutionalneuralnetworksforfeatherclassificationinchickens
AT haixuandeng researchnoteapplicationofconvolutionalneuralnetworksforfeatherclassificationinchickens
AT yujiahu researchnoteapplicationofconvolutionalneuralnetworksforfeatherclassificationinchickens
AT danxu researchnoteapplicationofconvolutionalneuralnetworksforfeatherclassificationinchickens
AT liutingwu researchnoteapplicationofconvolutionalneuralnetworksforfeatherclassificationinchickens
AT felixkwameamevor researchnoteapplicationofconvolutionalneuralnetworksforfeatherclassificationinchickens
AT yingjiewang researchnoteapplicationofconvolutionalneuralnetworksforfeatherclassificationinchickens
AT gangshu researchnoteapplicationofconvolutionalneuralnetworksforfeatherclassificationinchickens
AT xiaolingzhao researchnoteapplicationofconvolutionalneuralnetworksforfeatherclassificationinchickens