The Pattern Recognition in Cattle Brand using Bag of Visual Words and Support Vector Machines Multi-Class

Authors

  • Carlos Silva, Mr Federal University of Pampa http://orcid.org/0000-0001-8362-8984
  • Daniel Welfer, Dr Federal University of Santa Maria
  • Cláudia Dornelles, Mrs São Francisco de Assis City Hall

DOI:

https://doi.org/10.4114/intartif.vol21iss61pp1-13

Keywords:

Computer vision, Pattern recognition, Machine learning, Bag of Visual Words, Support Vector Machines Multi-Class.

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 Bag of Visual Words for extracting of characteristics from images of cattle brand and Support Vector Machines Multi-Class for classification. This method consists of six stages: a) select database of images; b) extract points of interest (SURF); c) create vocabulary (K-means); d) create vector of image characteristics (visual words); 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, reporting 86.02% of accuracy and 56.705 seconds of processing time, respectively.

Downloads

Download data is not yet available.

Author Biographies

Carlos Silva, Mr, Federal University of Pampa

Received his BSc degree in Computer Science at the Região da Campanha University (URCAMP), in 2010 and specialized in System Engineering at (ESAB), in 2012. Currently, is a Master’s student in Electrical Engineering at the Federal University of Pampa (UNIPAMPA). His projects focus on image analysis and processing, machine learning and computer vision. He is an SBC and IEEE’s active member.

Daniel Welfer, Dr, Federal University of Santa Maria

Is a Professor at the Federal University of Santa Maria (UFSM) in the Department of Applied Computing (DCOM).  He has concluded his PhD in Computer Science at the Federal University of Rio Grande do Sul (UFRGS), in 2011. His fields of interest are processing and analysis of medical images, mathematical morphology and hospital information systems. Currently, he is a permanent member of the graduate program in Computer Science (PPGI) at UFSM.

Cláudia Dornelles, Mrs, São Francisco de Assis City Hall

Received her BSc degree in Business Administration at the Norte do Paraná University (UNOPAR), in 2014. She is an administrative assistant in São Francisco de Assis City Hall, in Rio Grande do Sul, Brazil, and is responsible for recording and controlling cattle branding in the township.

Published

2018-03-21

How to Cite

Silva, C., Welfer, D., & Dornelles, C. (2018). The Pattern Recognition in Cattle Brand using Bag of Visual Words and Support Vector Machines Multi-Class. Inteligencia Artificial, 21(61), 1-13. https://doi.org/10.4114/intartif.vol21iss61pp1-13