The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Como base da boa gestão da criação e do seguro pecuário, o reconhecimento individual do gado leiteiro é uma questão importante no campo da gestão pecuária. Devido às limitações do método tradicional de identificação de vacas, como ser fácil de descartar e falsificar, ele não consegue mais atender às necessidades do moderno manejo inteligente de pastagens. Nos últimos anos, com o surgimento da tecnologia de visão computacional, a aprendizagem profunda desenvolveu-se rapidamente no campo do reconhecimento facial. A precisão do reconhecimento ultrapassou o nível do reconhecimento facial humano e tem sido amplamente utilizada no ambiente de produção. No entanto, a investigação sobre o reconhecimento facial de animais de grande porte, como o gado leiteiro, necessita de ser desenvolvida e melhorada. De acordo com a ideia de uma rede residual, um método aprimorado de rede neural convolucional (Res_5_2Net) para reconhecimento individual de vacas leiteiras é proposto com base nas imagens faciais de vacas leiteiras nesta carta. A precisão do reconhecimento em nosso banco de dados de rostos de vaca construído por nós mesmos (3012 conjuntos de treinamento, 1536 conjuntos de testes) pode chegar a 94.53%. Os resultados experimentais mostram que a eficiência da identificação de vacas leiteiras é efetivamente melhorada.
Zhi WENG
Inner Mongolia Agricultural University,Inner Mongolia University
Longzhen FAN
Inner Mongolia University
Yong ZHANG
Inner Mongolia Agricultural University
Zhiqiang ZHENG
Inner Mongolia University
Caili GONG
Inner Mongolia Agricultural University,Inner Mongolia University
Zhongyue WEI
Inner Mongolia University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Zhi WENG, Longzhen FAN, Yong ZHANG, Zhiqiang ZHENG, Caili GONG, Zhongyue WEI, "Facial Recognition of Dairy Cattle Based on Improved Convolutional Neural Network" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 6, pp. 1234-1238, June 2022, doi: 10.1587/transinf.2022EDP7008.
Abstract: As the basis of fine breeding management and animal husbandry insurance, individual recognition of dairy cattle is an important issue in the animal husbandry management field. Due to the limitations of the traditional method of cow identification, such as being easy to drop and falsify, it can no longer meet the needs of modern intelligent pasture management. In recent years, with the rise of computer vision technology, deep learning has developed rapidly in the field of face recognition. The recognition accuracy has surpassed the level of human face recognition and has been widely used in the production environment. However, research on the facial recognition of large livestock, such as dairy cattle, needs to be developed and improved. According to the idea of a residual network, an improved convolutional neural network (Res_5_2Net) method for individual dairy cow recognition is proposed based on dairy cow facial images in this letter. The recognition accuracy on our self-built cow face database (3012 training sets, 1536 test sets) can reach 94.53%. The experimental results show that the efficiency of identification of dairy cows is effectively improved.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDP7008/_p
Copiar
@ARTICLE{e105-d_6_1234,
author={Zhi WENG, Longzhen FAN, Yong ZHANG, Zhiqiang ZHENG, Caili GONG, Zhongyue WEI, },
journal={IEICE TRANSACTIONS on Information},
title={Facial Recognition of Dairy Cattle Based on Improved Convolutional Neural Network},
year={2022},
volume={E105-D},
number={6},
pages={1234-1238},
abstract={As the basis of fine breeding management and animal husbandry insurance, individual recognition of dairy cattle is an important issue in the animal husbandry management field. Due to the limitations of the traditional method of cow identification, such as being easy to drop and falsify, it can no longer meet the needs of modern intelligent pasture management. In recent years, with the rise of computer vision technology, deep learning has developed rapidly in the field of face recognition. The recognition accuracy has surpassed the level of human face recognition and has been widely used in the production environment. However, research on the facial recognition of large livestock, such as dairy cattle, needs to be developed and improved. According to the idea of a residual network, an improved convolutional neural network (Res_5_2Net) method for individual dairy cow recognition is proposed based on dairy cow facial images in this letter. The recognition accuracy on our self-built cow face database (3012 training sets, 1536 test sets) can reach 94.53%. The experimental results show that the efficiency of identification of dairy cows is effectively improved.},
keywords={},
doi={10.1587/transinf.2022EDP7008},
ISSN={1745-1361},
month={June},}
Copiar
TY - JOUR
TI - Facial Recognition of Dairy Cattle Based on Improved Convolutional Neural Network
T2 - IEICE TRANSACTIONS on Information
SP - 1234
EP - 1238
AU - Zhi WENG
AU - Longzhen FAN
AU - Yong ZHANG
AU - Zhiqiang ZHENG
AU - Caili GONG
AU - Zhongyue WEI
PY - 2022
DO - 10.1587/transinf.2022EDP7008
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2022
AB - As the basis of fine breeding management and animal husbandry insurance, individual recognition of dairy cattle is an important issue in the animal husbandry management field. Due to the limitations of the traditional method of cow identification, such as being easy to drop and falsify, it can no longer meet the needs of modern intelligent pasture management. In recent years, with the rise of computer vision technology, deep learning has developed rapidly in the field of face recognition. The recognition accuracy has surpassed the level of human face recognition and has been widely used in the production environment. However, research on the facial recognition of large livestock, such as dairy cattle, needs to be developed and improved. According to the idea of a residual network, an improved convolutional neural network (Res_5_2Net) method for individual dairy cow recognition is proposed based on dairy cow facial images in this letter. The recognition accuracy on our self-built cow face database (3012 training sets, 1536 test sets) can reach 94.53%. The experimental results show that the efficiency of identification of dairy cows is effectively improved.
ER -