Reconhecimento de Marcas de Gado utilizando Redes Neurais Convolucionais e Máquinas de Vetores de Suporte (Cattle Brand Recognition using Convolutional Neural Network and Support Vector Machines)

Carlos Silva (carlossilva@ieee.org)1, Daniel Welfer (welfer@gmail.com)2, Francisco Paulo Gioda (administracao@saofranciscodeassis.rs.gov.br)3, Cláudia Dornelles (administracao@saofranciscodeassis.rs.gov.br)3


1Universidade Federal do Pampa
2Universidade Federal de Santa Maria
3Prefeitura Municipal de São Francisco de Assis

This paper appears in: Revista IEEE América Latina

Publication Date: Feb. 2017
Volume: 15,   Issue: 2 
ISSN: 1548-0992


Abstract:
The recognition images of cattle brand in an automatic way is a necessity to governmental organs responsible for this activity. To help this process, this work presents a method that consists in using Convolutional Neural Network for extracting of characteristics from images of cattle brand and Support Vector Machines for classification. This method consists of six stages: a) select database of images; b) select pre-trained CNN; c) pre-process the images and apply CNN; d) extract images of features; e) train and sort images (SVM); f) evaluate the classification results. The accuracy of the method was tested on database of municipal city hall, where it achieved satisfactory results, comparable to other methods from the literature, reporting 93.28% of accuracy and 12.716 seconds of processing time, respectively.

Index Terms:
Recognition Images, Cattle Brands, Convolutional Neural Network, Support Vector Machines, Deep Learning   


Documents that cite this document
This function is not implemented yet.


[PDF Full-Text (581)]