Towards Early Poultry Health Prediction through Non-Invasive and Computer Vision-Based Dropping Classification
The use of artificial intelligence techniques with advanced computer vision techniques offers great potential for non-invasive health assessments in the poultry industry. Evaluating the condition of poultry by monitoring their droppings can be highly valuable as significant changes in consistency an...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/13/19/3041 |
| _version_ | 1827722907436974080 |
|---|---|
| author | Arnas Nakrosis Agne Paulauskaite-Taraseviciene Vidas Raudonis Ignas Narusis Valentas Gruzauskas Romas Gruzauskas Ingrida Lagzdinyte-Budnike |
| author_facet | Arnas Nakrosis Agne Paulauskaite-Taraseviciene Vidas Raudonis Ignas Narusis Valentas Gruzauskas Romas Gruzauskas Ingrida Lagzdinyte-Budnike |
| author_sort | Arnas Nakrosis |
| collection | DOAJ |
| description | The use of artificial intelligence techniques with advanced computer vision techniques offers great potential for non-invasive health assessments in the poultry industry. Evaluating the condition of poultry by monitoring their droppings can be highly valuable as significant changes in consistency and color can be indicators of serious and infectious diseases. While most studies have prioritized the classification of droppings into two categories (normal and abnormal), with some relevant studies dealing with up to five categories, this investigation goes a step further by employing image processing algorithms to categorize droppings into six classes, based on visual information indicating some level of abnormality. To ensure a diverse dataset, data were collected in three different poultry farms in Lithuania by capturing droppings on different types of litter. With the implementation of deep learning, the object detection rate reached 92.41% accuracy. A range of machine learning algorithms, including different deep learning architectures, has been explored and, based on the obtained results, we have proposed a comprehensive solution by combining different models for segmentation and classification purposes. The results revealed that the segmentation task achieved the highest accuracy of 0.88 in terms of the Dice coefficient employing the K-means algorithm. Meanwhile, YOLOv5 demonstrated the highest classification accuracy, achieving an ACC of 91.78%. |
| first_indexed | 2024-03-10T21:50:53Z |
| format | Article |
| id | doaj.art-bc62fc4829374216a315883fc73f091f |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-03-10T21:50:53Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-bc62fc4829374216a315883fc73f091f2023-11-19T13:59:24ZengMDPI AGAnimals2076-26152023-09-011319304110.3390/ani13193041Towards Early Poultry Health Prediction through Non-Invasive and Computer Vision-Based Dropping ClassificationArnas Nakrosis0Agne Paulauskaite-Taraseviciene1Vidas Raudonis2Ignas Narusis3Valentas Gruzauskas4Romas Gruzauskas5Ingrida Lagzdinyte-Budnike6Faculty of Informatics, Kaunas University of Technology, Studentu 50, 51368 Kaunas, LithuaniaFaculty of Informatics, Kaunas University of Technology, Studentu 50, 51368 Kaunas, LithuaniaArtificial Intelligence Centre, Kaunas University of Technology, K. Barsausko 59, 51423 Kaunas, LithuaniaFaculty of Informatics, Kaunas University of Technology, Studentu 50, 51368 Kaunas, LithuaniaArtificial Intelligence Centre, Kaunas University of Technology, K. Barsausko 59, 51423 Kaunas, LithuaniaArtificial Intelligence Centre, Kaunas University of Technology, K. Barsausko 59, 51423 Kaunas, LithuaniaFaculty of Informatics, Kaunas University of Technology, Studentu 50, 51368 Kaunas, LithuaniaThe use of artificial intelligence techniques with advanced computer vision techniques offers great potential for non-invasive health assessments in the poultry industry. Evaluating the condition of poultry by monitoring their droppings can be highly valuable as significant changes in consistency and color can be indicators of serious and infectious diseases. While most studies have prioritized the classification of droppings into two categories (normal and abnormal), with some relevant studies dealing with up to five categories, this investigation goes a step further by employing image processing algorithms to categorize droppings into six classes, based on visual information indicating some level of abnormality. To ensure a diverse dataset, data were collected in three different poultry farms in Lithuania by capturing droppings on different types of litter. With the implementation of deep learning, the object detection rate reached 92.41% accuracy. A range of machine learning algorithms, including different deep learning architectures, has been explored and, based on the obtained results, we have proposed a comprehensive solution by combining different models for segmentation and classification purposes. The results revealed that the segmentation task achieved the highest accuracy of 0.88 in terms of the Dice coefficient employing the K-means algorithm. Meanwhile, YOLOv5 demonstrated the highest classification accuracy, achieving an ACC of 91.78%.https://www.mdpi.com/2076-2615/13/19/3041poultrydroppingscomputer visiondeep learningsegmentationclassification |
| spellingShingle | Arnas Nakrosis Agne Paulauskaite-Taraseviciene Vidas Raudonis Ignas Narusis Valentas Gruzauskas Romas Gruzauskas Ingrida Lagzdinyte-Budnike Towards Early Poultry Health Prediction through Non-Invasive and Computer Vision-Based Dropping Classification Animals poultry droppings computer vision deep learning segmentation classification |
| title | Towards Early Poultry Health Prediction through Non-Invasive and Computer Vision-Based Dropping Classification |
| title_full | Towards Early Poultry Health Prediction through Non-Invasive and Computer Vision-Based Dropping Classification |
| title_fullStr | Towards Early Poultry Health Prediction through Non-Invasive and Computer Vision-Based Dropping Classification |
| title_full_unstemmed | Towards Early Poultry Health Prediction through Non-Invasive and Computer Vision-Based Dropping Classification |
| title_short | Towards Early Poultry Health Prediction through Non-Invasive and Computer Vision-Based Dropping Classification |
| title_sort | towards early poultry health prediction through non invasive and computer vision based dropping classification |
| topic | poultry droppings computer vision deep learning segmentation classification |
| url | https://www.mdpi.com/2076-2615/13/19/3041 |
| work_keys_str_mv | AT arnasnakrosis towardsearlypoultryhealthpredictionthroughnoninvasiveandcomputervisionbaseddroppingclassification AT agnepaulauskaitetaraseviciene towardsearlypoultryhealthpredictionthroughnoninvasiveandcomputervisionbaseddroppingclassification AT vidasraudonis towardsearlypoultryhealthpredictionthroughnoninvasiveandcomputervisionbaseddroppingclassification AT ignasnarusis towardsearlypoultryhealthpredictionthroughnoninvasiveandcomputervisionbaseddroppingclassification AT valentasgruzauskas towardsearlypoultryhealthpredictionthroughnoninvasiveandcomputervisionbaseddroppingclassification AT romasgruzauskas towardsearlypoultryhealthpredictionthroughnoninvasiveandcomputervisionbaseddroppingclassification AT ingridalagzdinytebudnike towardsearlypoultryhealthpredictionthroughnoninvasiveandcomputervisionbaseddroppingclassification |