Towards on-farm pig face recognition using convolutional neural networks
Towards on-farm pig face recognition using convolutional neural networks
复制标题
DOI：
10.1016/j.compind.2018.02.016
复制
发表时间：
2018-06-01
影响因子：
10
通讯作者：
Grieve, Bruce
中科院分区：
文献类型：
--
作者：
Hansen, Mark E.;Smith, Melvyn L.;Grieve, Bruce
近年来，随着集约化做法的继续采用和需要精确的客观测量（如重量），猪和牛等牲畜个体的识别已成为一个紧迫的问题。目前的最佳实践涉及使用RFID标签，这对农民来说是耗时的，对动物来说是痛苦的。为了克服这一点，非侵入性的生物特征被提出使用的动物的脸。我们在一个农场环境中测试了这一点，在10头猪身上使用了三种来自人脸识别文献的技术：Fisherfaces，VGG-Face预训练的人脸卷积神经网络（CNN）模型和我们自己的CNN模型，我们使用人工增强的数据集进行训练。我们的研究结果表明，准确的个体猪识别是可能的，准确率为96.7%的1553图像。使用Grad-CAM的类激活映射用于显示我们的网络用于区分猪的区域。(C)2018爱思唯尔B. V.保留所有权利。
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. (C) 2018 Elsevier B.V. All rights reserved.