High-Accuracy Recognition Method for Diseased Chicken Feces Based on Image and Text Information Fusion
Poultry feces, a critical biomarker for health assessment, requires timely and accurate pathological identification for food safety. Conventional visual-only methods face limitations due to environmental sensitivity and high visual similarity among feces from different diseases. To address this, we...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/15/15/2158 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849770605191102464 |
|---|---|
| author | Duanli Yang Zishang Tian Jianzhong Xi Hui Chen Erdong Sun Lianzeng Wang |
| author_facet | Duanli Yang Zishang Tian Jianzhong Xi Hui Chen Erdong Sun Lianzeng Wang |
| author_sort | Duanli Yang |
| collection | DOAJ |
| description | Poultry feces, a critical biomarker for health assessment, requires timely and accurate pathological identification for food safety. Conventional visual-only methods face limitations due to environmental sensitivity and high visual similarity among feces from different diseases. To address this, we propose MMCD (Multimodal Chicken-feces Diagnosis), a ResNet50-based multimodal fusion model leveraging semantic complementarity between images and descriptive text to enhance diagnostic precision. Key innovations include the following: (1) Integrating MASA(Manhattan self-attention)and DSconv (Depthwise Separable convolution) into the backbone network to mitigate feature confusion. (2) Utilizing a pre-trained BERT to extract textual semantic features, reducing annotation dependency and cost. (3) Designing a lightweight Gated Cross-Attention (GCA) module for dynamic multimodal fusion, achieving a 41% parameter reduction versus cross-modal transformers. Experiments demonstrate that MMCD significantly outperforms single-modal baselines in Accuracy (+8.69%), Recall (+8.72%), Precision (+8.67%), and F1 score (+8.72%). It surpasses simple feature concatenation by 2.51–2.82% and reduces parameters by 7.5M and computations by 1.62 GFLOPs versus the base ResNet50. This work validates multimodal fusion’s efficacy in pathological fecal detection, providing a theoretical and technical foundation for agricultural health monitoring systems. |
| format | Article |
| id | doaj-art-0ebd973a2d63452c9e43daeb07971f68 |
| institution | DOAJ |
| issn | 2076-2615 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj-art-0ebd973a2d63452c9e43daeb07971f682025-08-20T03:02:56ZengMDPI AGAnimals2076-26152025-07-011515215810.3390/ani15152158High-Accuracy Recognition Method for Diseased Chicken Feces Based on Image and Text Information FusionDuanli Yang0Zishang Tian1Jianzhong Xi2Hui Chen3Erdong Sun4Lianzeng Wang5College of Information Science and Technology, Hebei Agricultural University, Baoding 071001, ChinaCollege of Information Science and Technology, Hebei Agricultural University, Baoding 071001, ChinaGraduate School, Hebei Agricultural University, Baoding 071001, ChinaCollege of Animal Science and Technology, Hebei Agricultural University, Baoding 071001, ChinaHebei Taomu Geda Agricultural Science and Technology Co., Baoding 074300, ChinaHebei Layer Industry Technology Research Institute, Handan 056007, ChinaPoultry feces, a critical biomarker for health assessment, requires timely and accurate pathological identification for food safety. Conventional visual-only methods face limitations due to environmental sensitivity and high visual similarity among feces from different diseases. To address this, we propose MMCD (Multimodal Chicken-feces Diagnosis), a ResNet50-based multimodal fusion model leveraging semantic complementarity between images and descriptive text to enhance diagnostic precision. Key innovations include the following: (1) Integrating MASA(Manhattan self-attention)and DSconv (Depthwise Separable convolution) into the backbone network to mitigate feature confusion. (2) Utilizing a pre-trained BERT to extract textual semantic features, reducing annotation dependency and cost. (3) Designing a lightweight Gated Cross-Attention (GCA) module for dynamic multimodal fusion, achieving a 41% parameter reduction versus cross-modal transformers. Experiments demonstrate that MMCD significantly outperforms single-modal baselines in Accuracy (+8.69%), Recall (+8.72%), Precision (+8.67%), and F1 score (+8.72%). It surpasses simple feature concatenation by 2.51–2.82% and reduces parameters by 7.5M and computations by 1.62 GFLOPs versus the base ResNet50. This work validates multimodal fusion’s efficacy in pathological fecal detection, providing a theoretical and technical foundation for agricultural health monitoring systems.https://www.mdpi.com/2076-2615/15/15/2158multimodalResNet50BERTchicken diseasecross-attention |
| spellingShingle | Duanli Yang Zishang Tian Jianzhong Xi Hui Chen Erdong Sun Lianzeng Wang High-Accuracy Recognition Method for Diseased Chicken Feces Based on Image and Text Information Fusion Animals multimodal ResNet50 BERT chicken disease cross-attention |
| title | High-Accuracy Recognition Method for Diseased Chicken Feces Based on Image and Text Information Fusion |
| title_full | High-Accuracy Recognition Method for Diseased Chicken Feces Based on Image and Text Information Fusion |
| title_fullStr | High-Accuracy Recognition Method for Diseased Chicken Feces Based on Image and Text Information Fusion |
| title_full_unstemmed | High-Accuracy Recognition Method for Diseased Chicken Feces Based on Image and Text Information Fusion |
| title_short | High-Accuracy Recognition Method for Diseased Chicken Feces Based on Image and Text Information Fusion |
| title_sort | high accuracy recognition method for diseased chicken feces based on image and text information fusion |
| topic | multimodal ResNet50 BERT chicken disease cross-attention |
| url | https://www.mdpi.com/2076-2615/15/15/2158 |
| work_keys_str_mv | AT duanliyang highaccuracyrecognitionmethodfordiseasedchickenfecesbasedonimageandtextinformationfusion AT zishangtian highaccuracyrecognitionmethodfordiseasedchickenfecesbasedonimageandtextinformationfusion AT jianzhongxi highaccuracyrecognitionmethodfordiseasedchickenfecesbasedonimageandtextinformationfusion AT huichen highaccuracyrecognitionmethodfordiseasedchickenfecesbasedonimageandtextinformationfusion AT erdongsun highaccuracyrecognitionmethodfordiseasedchickenfecesbasedonimageandtextinformationfusion AT lianzengwang highaccuracyrecognitionmethodfordiseasedchickenfecesbasedonimageandtextinformationfusion |