Towards on-farm pig face recognition using convolutional neural networks

• Published in: Computers in industry 2018-06, Vol.98, p.145-152
• Main Authors: Hansen, Mark F., Smith, Melvyn L., Smith, Lyndon N., Salter, Michael G., Baxter, Emma M., Farish, Marianne, Grieve, Bruce
• Format: Article
• Language: English
• Subjects: Biometrics; Convolutional neural network; Deep learning; Pig face recognition
• ISSN: 0166-3615; 1872-6194
• DOI: 10.1016/j.compind.2018.02.016

•Face recognition for humans is a well-studied and proven biometric.•Precision agriculture requires individual animals to be identified reliably.•Current methods e.g. RFID have shortcomings (range, distressing to fit).•We adapt approaches from human literature to on farm pig-face recognition.•Accuracy of 96.7% is achieved on 1553 images of 10 pigs using our own CNN. Identification of individual livestock such as pigs and cows has become a pressing issue in recent years as intensification practices continue to be adopted and precise objective measurements are required (e.g. weight). Current best practice involves the use of RFID tags which are time-consuming for the farmer and distressing for the animal to fit. To overcome this, non-invasive biometrics are proposed by using the face of the animal. We test this in a farm environment, on 10 individual pigs using three techniques adopted from the human face recognition literature: Fisherfaces, the VGG-Face pre-trained face convolutional neural network (CNN) model and our own CNN model that we train using an artificially augmented data set. Our results show that accurate individual pig recognition is possible with accuracy rates of 96.7% on 1553 images. Class Activated Mapping using Grad-CAM is used to show the regions that our network uses to discriminate between pigs.