Image processing steps applied in our research.
<div><p>Accurate estimation of cattle weight is essential for effective farm management, health assessment, and productivity optimization. Traditional manual methods for weight estimation, however, are labor-intensive, time-consuming, and prone to inaccuracies. Recent advances in compute...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , |
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1852014874921533440 |
|---|---|
| author | Md Junayed Hossain (22615268) |
| author2 | Jannatul Ferdaus (22140270) Ashraful Islam (1283403) M. Ashraful Amin (22615271) |
| author2_role | author author author |
| author_facet | Md Junayed Hossain (22615268) Jannatul Ferdaus (22140270) Ashraful Islam (1283403) M. Ashraful Amin (22615271) |
| author_role | author |
| dc.creator.none.fl_str_mv | Md Junayed Hossain (22615268) Jannatul Ferdaus (22140270) Ashraful Islam (1283403) M. Ashraful Amin (22615271) |
| dc.date.none.fl_str_mv | 2025-11-13T18:52:46Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0336434.g004 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Image_processing_steps_applied_in_our_research_/30614225 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Sociology Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified precise feature extraction mean absolute error less accurate predictions error case analysis demonstrates superior accuracy input data quality effective farm management pretrained efficientnetb3 model model significantly surpasses traditional manual methods associated weight data livestock weight estimation explainable cnn framework traditional regression models traditional methods weight estimation image data linear regression framework designed effective approach weight prediction cattle weight yolov5 algorithm study emphasizes results show recent advances random forest provide insights productivity optimization one variation mse ), making process low mae including normalization histogram equalization health assessment first leveraged face challenges especially cnn deep learning custom cnn conventional models computer vision cnn models cnn ). cattle images based approach 85 kg 02 kg |
| dc.title.none.fl_str_mv | Image processing steps applied in our research. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>Accurate estimation of cattle weight is essential for effective farm management, health assessment, and productivity optimization. Traditional manual methods for weight estimation, however, are labor-intensive, time-consuming, and prone to inaccuracies. Recent advances in computer vision have facilitated the automation of weight prediction from image data. However, traditional regression models, such as Random Forest and Linear Regression, face challenges in capturing the complex, nonlinear relationships within image data, leading to less accurate predictions. To address these issues, we introduce CattleNet-XAI, a framework designed for both efficiency and explainability, which utilizes a custom Convolutional Neural Network (CNN). For the CNN-based approach, we incorporated advanced image preprocessing techniques, including normalization and histogram equalization, to enhance the input data quality. We compared its performance with other CNN models, the pretrained EfficientNetB3 model, and traditional machine learning methods like Random Forest and Linear Regression. For the traditional methods, we first leveraged the YOLOv5 algorithm for precise feature extraction from the cattle images. All the models were trained and evaluated on a dataset of cattle images and associated weight data, with performance measured by Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). Our results show that one variation of our custom CNN (3Conv3Dense) model significantly surpasses other conventional models, achieving a low MAE of 18.02 kg and an RMSE of 19.85 kg, which demonstrates superior accuracy. We also present LIME visualization and error case analysis to provide insights into the decision-making process of the model. This study emphasizes the capability of deep learning, especially CNN, in automating and enhancing the precision of livestock weight estimation, offering a modern and effective approach to cattle management.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_ddb0f091ce9dbaa405e3bbcab8b8a1f3 |
| identifier_str_mv | 10.1371/journal.pone.0336434.g004 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/30614225 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Image processing steps applied in our research.Md Junayed Hossain (22615268)Jannatul Ferdaus (22140270)Ashraful Islam (1283403)M. Ashraful Amin (22615271)SociologyBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedprecise feature extractionmean absolute errorless accurate predictionserror case analysisdemonstrates superior accuracyinput data qualityeffective farm managementpretrained efficientnetb3 modelmodel significantly surpassestraditional manual methodsassociated weight datalivestock weight estimationexplainable cnn frameworktraditional regression modelstraditional methodsweight estimationimage datalinear regressionframework designedeffective approachweight predictioncattle weightyolov5 algorithmstudy emphasizesresults showrecent advancesrandom forestprovide insightsproductivity optimizationone variationmse ),making processlow maeincluding normalizationhistogram equalizationhealth assessmentfirst leveragedface challengesespecially cnndeep learningcustom cnnconventional modelscomputer visioncnn modelscnn ).cattle imagesbased approach85 kg02 kg<div><p>Accurate estimation of cattle weight is essential for effective farm management, health assessment, and productivity optimization. Traditional manual methods for weight estimation, however, are labor-intensive, time-consuming, and prone to inaccuracies. Recent advances in computer vision have facilitated the automation of weight prediction from image data. However, traditional regression models, such as Random Forest and Linear Regression, face challenges in capturing the complex, nonlinear relationships within image data, leading to less accurate predictions. To address these issues, we introduce CattleNet-XAI, a framework designed for both efficiency and explainability, which utilizes a custom Convolutional Neural Network (CNN). For the CNN-based approach, we incorporated advanced image preprocessing techniques, including normalization and histogram equalization, to enhance the input data quality. We compared its performance with other CNN models, the pretrained EfficientNetB3 model, and traditional machine learning methods like Random Forest and Linear Regression. For the traditional methods, we first leveraged the YOLOv5 algorithm for precise feature extraction from the cattle images. All the models were trained and evaluated on a dataset of cattle images and associated weight data, with performance measured by Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). Our results show that one variation of our custom CNN (3Conv3Dense) model significantly surpasses other conventional models, achieving a low MAE of 18.02 kg and an RMSE of 19.85 kg, which demonstrates superior accuracy. We also present LIME visualization and error case analysis to provide insights into the decision-making process of the model. This study emphasizes the capability of deep learning, especially CNN, in automating and enhancing the precision of livestock weight estimation, offering a modern and effective approach to cattle management.</p></div>2025-11-13T18:52:46ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0336434.g004https://figshare.com/articles/figure/Image_processing_steps_applied_in_our_research_/30614225CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/306142252025-11-13T18:52:46Z |
| spellingShingle | Image processing steps applied in our research. Md Junayed Hossain (22615268) Sociology Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified precise feature extraction mean absolute error less accurate predictions error case analysis demonstrates superior accuracy input data quality effective farm management pretrained efficientnetb3 model model significantly surpasses traditional manual methods associated weight data livestock weight estimation explainable cnn framework traditional regression models traditional methods weight estimation image data linear regression framework designed effective approach weight prediction cattle weight yolov5 algorithm study emphasizes results show recent advances random forest provide insights productivity optimization one variation mse ), making process low mae including normalization histogram equalization health assessment first leveraged face challenges especially cnn deep learning custom cnn conventional models computer vision cnn models cnn ). cattle images based approach 85 kg 02 kg |
| status_str | publishedVersion |
| title | Image processing steps applied in our research. |
| title_full | Image processing steps applied in our research. |
| title_fullStr | Image processing steps applied in our research. |
| title_full_unstemmed | Image processing steps applied in our research. |
| title_short | Image processing steps applied in our research. |
| title_sort | Image processing steps applied in our research. |
| topic | Sociology Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified precise feature extraction mean absolute error less accurate predictions error case analysis demonstrates superior accuracy input data quality effective farm management pretrained efficientnetb3 model model significantly surpasses traditional manual methods associated weight data livestock weight estimation explainable cnn framework traditional regression models traditional methods weight estimation image data linear regression framework designed effective approach weight prediction cattle weight yolov5 algorithm study emphasizes results show recent advances random forest provide insights productivity optimization one variation mse ), making process low mae including normalization histogram equalization health assessment first leveraged face challenges especially cnn deep learning custom cnn conventional models computer vision cnn models cnn ). cattle images based approach 85 kg 02 kg |