Sheep Identification Using a Hybrid Deep Learning and Bayesian Optimization Approach

Abstract

Sheep are considered a necessary source of food production worldwide. Therefore, the sheep identification is vital for managing breeding and disease. Moreover, it is the only guarantee of an individual's ownership. Therefore, in this paper, sheep identities were recognized by a deep convolutional neural network using facial bio-metrics. To obtain the best possible accuracy, different neural networks designs were surveyed and tested in this paper. The Bayesian optimization was used to automatically set the parameters for a convolutional neural network; in addition, the AlexNet configuration was also examined in this paper. In this paper, the sheep recognition algorithms were tested on a data set of 52 sheep. Not more than 10 images were taken of each sheep in different postures. Thus, the data augmentation methodologies such as rotation, reflection, scaling, blurring, and brightness modification were applied; 1000 images of each sheep were obtained for training and validation. The experiments conducted in this paper achieved an accuracy of 98%. Our approach outperforms previous approaches for sheep identification. INDEX TERMS Bayesian optimization, convolutional neural network, deep learning.

Practices and Applications of Convolutional Neural Network-Based Computer Vision Systems in Animal Farming: A Review

“…The distances of 1-5 m were mostly utilized, which were fitted to dimensions of modern animal houses and simultaneously advantageous on capturing most details of target animals. For those applications requiring clear and obvious features of target objects (e.g., faces of animals), close distances (e.g., 0.5 m) were preferred [ 55 ]. An unmanned aerial vehicle (UAV) was utilized to count animals at long range distances (e.g., 80 m away from animals), which minimized the interference of detection [ 56 ].…”

“…can also supply diverse data [ 54 ]. Additionally, adjusting cameras is another strategy of including variations and may change shapes, sizes, and poses of target animals in recorded images, such as moving cameras around target animals [ 63 ], adjusting distances between cameras and target animals [ 55 ], modifying heights and tilting angles of cameras [ 64 ], etc.…”

“…However, lighting conditions in farms are complex and diverse, and color-space patterns learned from development datasets may not be matched to those in real applications, which may lead to poor generalization performance [ 115 ]. One solution was to convert RGB images (three channels) into grayscale images (one channel) [ 48 , 55 , 70 , 88 , 116 ], so that attention of models can be diverted from object colors to learning patterns of objects. Additionally, hue, saturation, and value (HSV) imaging was not as sensitive to illumination changes as RGB imaging and may be advantageous on detecting characteristics of colorful target objects [ 114 ].…”

“…One strategy to improve efficiency is to crop an image into regions of interest before processing. The cropping can be based on a whole body of an animal [ 80 , 117 , 118 ], parts (e.g., face, trunk) of an animal [ 55 , 107 ], or areas around facilities (e.g., enrichment, feeder, and drinker) [ 86 , 114 , 119 ]. As for some large images, cropping them into small and regular pieces of images can reduce computational resources and improve processing speed [ 56 , 64 , 106 , 120 ].…”

“…Relevant strategies (e.g., distorting, translating, shifting, reflecting, shearing, etc.) were also utilized in animal farming [ 55 , 73 ]. Cropping is to randomly or sequentially cut small pieces of patches from original images [ 130 ].…”