Cattle Brand Recognition using Convolutional Neural Network and Support Vector Machines

Silva, Carlos; Welfer, Daniel; Gioda, Francisco Paulo; Dornelles, Cláudia

doi:10.1109/tla.2017.7854627

Cited by 24 publications

(12 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Since there is no 3D PCD dataset for animals, all data need to be collected manually, so the amount of data obtained is limited [56]. However, a large amount of training data is needed in the training process of neural networks to prevent overfitting.…”

Section: Methodsmentioning

confidence: 99%

Body Dimension Measurements of Qinchuan Cattle with Transfer Learning from LiDAR Sensing

Huang

Guo

Rao

et al. 2019

Sensors

View full text Add to dashboard Cite

For the time-consuming and stressful body measuring task of Qinchuan cattle and farmers, the demand for the automatic measurement of body dimensions has become more and more urgent. It is necessary to explore automatic measurements with deep learning to improve breeding efficiency and promote the development of industry. In this paper, a novel approach to measuring the body dimensions of live Qinchuan cattle with on transfer learning is proposed. Deep learning of the Kd-network was trained with classical three-dimensional (3D) point cloud datasets (PCD) of the ShapeNet datasets. After a series of processes of PCD sensed by the light detection and ranging (LiDAR) sensor, the cattle silhouettes could be extracted, which after augmentation could be applied as an input layer to the Kd-network. With the output of a convolutional layer of the trained deep model, the output layer of the deep model could be applied to pre-train the full connection network. The TrAdaBoost algorithm was employed to transfer the pre-trained convolutional layer and full connection of the deep model. To classify and recognize the PCD of the cattle silhouette, the average accuracy rate after training with transfer learning could reach up to 93.6%. On the basis of silhouette extraction, the candidate region of the feature surface shape could be extracted with mean curvature and Gaussian curvature. After the computation of the FPFH (fast point feature histogram) of the surface shape, the center of the feature surface could be recognized and the body dimensions of the cattle could finally be calculated. The experimental results showed that the comprehensive error of body dimensions was close to 2%, which could provide a feasible approach to the non-contact observations of the bodies of large physique livestock without any human intervention.

show abstract

Section: Methodsmentioning

confidence: 99%

Body Dimension Measurements of Qinchuan Cattle with Transfer Learning from LiDAR Sensing

Huang

Guo

Rao

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…In the third stage of the training process, it was trained a binary classifier using a Support Vector Machine with linear kernel 4,22 , which aims to classify two classes: "Theft" and "No Theft". Fig.…”

Section: Support Vector Machine Linear Predictor For the Detection Ofmentioning

confidence: 99%

“…In many C2IS, the Video Surveillance System is a fundamental source of strategic information, however, it is common that some events (like theft) can't be detected by Video Surveillance operators, because commonly there are more cameras than one operator can manage. development and implementation of a prototype of street theft detector based on deep learning, specifically using the R-CNN (Region-Based Convolutional Network) technique 2 , which is implemented using three different architectures of CNN (Convolutional Neural Network) 3,4 , AlexNet 5 , VGG16 6 and VGG19 6 . Finally, the prototypes were tested with information from the Video Surveillance system of the National Police of Colombia, with the support of the Telematics Office, in order to conclude which architecture may have the lowest computational cost for a future implementation in the National Police of Colombia.…”

Section: Introductionmentioning

confidence: 99%

Reduced computational cost prototype for street theft detection based on depth decrement in Convolutional Neural Network. Application to Command and Control Information Systems (C2IS) in the National Police of Colombia.

Suarez-Paez¹,

Salcedo-Gonzalez²,

Esteve³

et al. 2018

IJCIS

View full text Add to dashboard Cite

This paper shows the implementation of a prototype of street theft detector using the deep learning technique R-CNN (Region-Based Convolutional Network), applied in the Command and Control Information System (C2IS) of National Police of Colombia, the prototype is implemented using three models of CNN (Convolutional Neural Network), AlexNet, VGG16 and VGG19 comparing their computational cost measuring the image processing time, according to the complexity (depth) of each model. Finally, we conclude which model has the lowest computational cost and is more useful for the case of the National Police of Colombia.

show abstract

“…A partir da matriz de confusão é possível obter o número de classificações corretas e previstas pelo classificador em cada classe, no conjunto de imagens utilizadas para teste [29].…”

Section: Matriz De Confusãounclassified

Análise Comparativa de Redes Neurais Convolucionais no Reconhecimento de Cenas

Souza¹,

Silva²,

Santos³

et al. 2020

Anais Do XI Computer on the Beach - COTB '20

View full text Add to dashboard Cite

This paper aims to compare the convolutional neural networks(CNNs): ResNet50, InceptionV3, and InceptionResNetV2 tested withand without pre-trained weights on the ImageNet database in orderto solve the scene recognition problem. The results showed that thepre-trained ResNet50 achieved the best performance with an averageaccuracy of 99.82% in training and 85.53% in the test, while theworst result was attributed to the ResNet50 without pre-training,with 88.76% and 71.66% of average accuracy in training and testing,respectively. The main contribution of this work is the direct comparisonbetween the CNNs widely applied in the literature, that is,to enable a better selection of the algorithms in the various scenerecognition applications.

show abstract

Cattle Brand Recognition using Convolutional Neural Network and Support Vector Machines

Cited by 24 publications

References 8 publications

Body Dimension Measurements of Qinchuan Cattle with Transfer Learning from LiDAR Sensing

Body Dimension Measurements of Qinchuan Cattle with Transfer Learning from LiDAR Sensing

Reduced computational cost prototype for street theft detection based on depth decrement in Convolutional Neural Network. Application to Command and Control Information Systems (C2IS) in the National Police of Colombia.

Análise Comparativa de Redes Neurais Convolucionais no Reconhecimento de Cenas

Contact Info

Product

Resources

About