Abstract: Individual identification technology was the primary requirement of automatic production techniques,including intelligence weighting,body condition scoring,body shape identification,and behavior monitoring.Individual cattle identification methods were categorized and elaborated in current review,that the research progress of different individual cattle identification methods including traditional,biometric,and deep learning methods were introduced,especially the difficulties of applying deep learning method in practice were discussed.Moreover,the advantages and disadvantages of different identification methods were analyzed.Traditional identification methods such as ear notching,ear tattooing,and hot branding identified cattle relies on manual labor,which had low identification accuracy and efficiency,and ignored animal welfare and mark persistence.Radio frequency identification techniques provided an automatic identifying protocol that elevated the efficiency but the data security could not be guaranteed.With the development of image recognition technology and deep learning methods,non-contact,safe and efficient cattle intelligent recognition had been realized with the technology based on biometric recognition and deep learning methods.However,the biometric identification method based on nose print,retinal blood vessels and iris had poor practicability,because the ideal image was difficult to obtain.Based on deep neural networks learning of image features,the deep learning method was more practical and promising in complex dairy farm circumstances.What’s more,different individual identification methods were compared,and the research on individual cattle identification technology was prospected in current review.

Key words: cattle; individual identification; biometric identification; deep learning