Sheep face recognition and classification based on an improved MobilenetV2 neural network
Large-scale sheep farming has conventionally relied on barcodes and ear tags, devices that can be difficult to implement and maintain, for sheep identification and tracking. Biological data have also been used for tracking in recent years but have not been widely adopted due to the difficulty and hi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2023-02-01
|
| Series: | International Journal of Advanced Robotic Systems |
| Online Access: | https://doi.org/10.1177/17298806231152969 |
| _version_ | 1811169173013790720 |
|---|---|
| author | Yue Pang Wenbo Yu Yongan Zhang Chuanzhong Xuan Pei Wu |
| author_facet | Yue Pang Wenbo Yu Yongan Zhang Chuanzhong Xuan Pei Wu |
| author_sort | Yue Pang |
| collection | DOAJ |
| description | Large-scale sheep farming has conventionally relied on barcodes and ear tags, devices that can be difficult to implement and maintain, for sheep identification and tracking. Biological data have also been used for tracking in recent years but have not been widely adopted due to the difficulty and high costs of data collection. To address these issues, a noncontact facial recognition technique is proposed in this study, in which training data were acquired in natural conditions using a series of video cameras, as Dupo sheep walked freely through a gate. A key frame extraction algorithm was then applied to automatically generate sheep face data sets representing various poses. An improved MobilenetV2 framework, termed Order-MobilenetV2 (O-MobilenetV2), was developed from an existing advanced convolutional neural network and used to improve the performance of feature extraction. In addition, O-MobilenetV2 includes a unique conv3x3 deep convolution module, which facilitated higher accuracy while reducing the number of required calculations by approximately two-thirds. A series of validation tests were performed in which the algorithm identified individual sheep using facial features, with the proposed model achieving the highest accuracy (95.88%) among comparable algorithms. In addition to high accuracy and low processing times, this approach does not require significant data pre-processing, which is common among other models and prohibitive for large sheep populations. This combination of simple operation, low equipment costs, and high robustness to variable sheep postures and environmental conditions makes our proposed technique a viable new strategy for sheep facial recognition and tracking. |
| first_indexed | 2024-04-10T16:39:07Z |
| format | Article |
| id | doaj.art-97e4c011d30d4d43a22f4c5ec2bb85a4 |
| institution | Directory Open Access Journal |
| issn | 1729-8814 |
| language | English |
| last_indexed | 2024-04-10T16:39:07Z |
| publishDate | 2023-02-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | International Journal of Advanced Robotic Systems |
| spelling | doaj.art-97e4c011d30d4d43a22f4c5ec2bb85a42023-02-08T09:33:20ZengSAGE PublishingInternational Journal of Advanced Robotic Systems1729-88142023-02-012010.1177/17298806231152969Sheep face recognition and classification based on an improved MobilenetV2 neural networkYue Pang0Wenbo Yu1Yongan Zhang2Chuanzhong Xuan3Pei Wu4 College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot, China College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot, China College of Computer and Information Engineering, Inner Mongolia Agricultural University, Hohhot, China College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot, China College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot, ChinaLarge-scale sheep farming has conventionally relied on barcodes and ear tags, devices that can be difficult to implement and maintain, for sheep identification and tracking. Biological data have also been used for tracking in recent years but have not been widely adopted due to the difficulty and high costs of data collection. To address these issues, a noncontact facial recognition technique is proposed in this study, in which training data were acquired in natural conditions using a series of video cameras, as Dupo sheep walked freely through a gate. A key frame extraction algorithm was then applied to automatically generate sheep face data sets representing various poses. An improved MobilenetV2 framework, termed Order-MobilenetV2 (O-MobilenetV2), was developed from an existing advanced convolutional neural network and used to improve the performance of feature extraction. In addition, O-MobilenetV2 includes a unique conv3x3 deep convolution module, which facilitated higher accuracy while reducing the number of required calculations by approximately two-thirds. A series of validation tests were performed in which the algorithm identified individual sheep using facial features, with the proposed model achieving the highest accuracy (95.88%) among comparable algorithms. In addition to high accuracy and low processing times, this approach does not require significant data pre-processing, which is common among other models and prohibitive for large sheep populations. This combination of simple operation, low equipment costs, and high robustness to variable sheep postures and environmental conditions makes our proposed technique a viable new strategy for sheep facial recognition and tracking.https://doi.org/10.1177/17298806231152969 |
| spellingShingle | Yue Pang Wenbo Yu Yongan Zhang Chuanzhong Xuan Pei Wu Sheep face recognition and classification based on an improved MobilenetV2 neural network International Journal of Advanced Robotic Systems |
| title | Sheep face recognition and classification based on an improved MobilenetV2 neural network |
| title_full | Sheep face recognition and classification based on an improved MobilenetV2 neural network |
| title_fullStr | Sheep face recognition and classification based on an improved MobilenetV2 neural network |
| title_full_unstemmed | Sheep face recognition and classification based on an improved MobilenetV2 neural network |
| title_short | Sheep face recognition and classification based on an improved MobilenetV2 neural network |
| title_sort | sheep face recognition and classification based on an improved mobilenetv2 neural network |
| url | https://doi.org/10.1177/17298806231152969 |
| work_keys_str_mv | AT yuepang sheepfacerecognitionandclassificationbasedonanimprovedmobilenetv2neuralnetwork AT wenboyu sheepfacerecognitionandclassificationbasedonanimprovedmobilenetv2neuralnetwork AT yonganzhang sheepfacerecognitionandclassificationbasedonanimprovedmobilenetv2neuralnetwork AT chuanzhongxuan sheepfacerecognitionandclassificationbasedonanimprovedmobilenetv2neuralnetwork AT peiwu sheepfacerecognitionandclassificationbasedonanimprovedmobilenetv2neuralnetwork |