IDENTIFICATION OF BOVINES THROUGH RECOGNITION OF IMAGES PATTERNS OF THE MUZZLE USING ARTIFICIAL NEURAL NETS

• Grant number: 09/06714-0
• Support Opportunities: Scholarships in Brazil - Master
• Start date: March 01, 2010
• End date: April 30, 2011
• Field of knowledge: Agronomical Sciences - Animal Husbandry - Animal Production
• Principal Investigator: Ernane José Xavier Costa
• Grantee: Carolina Melleiro Gimenez
• Host Institution: Faculdade de Zootecnia e Engenharia de Alimentos (FZEA). Universidade de São Paulo (USP). Pirassununga , SP, Brazil

Abstract

The present study proposes to analyze the bovine's muzzle with the intention of proving that's a permanent and unique characteristic of the animal, abling their identification. For this will be used 50 bovines of the Nelore race, which will be collected twenty images of each animal in different angles and distance totalizing a thousand images to the formation of the data base and be analyzed. For the processing of the captured images and extracting permanent characteristics will be used the MATLAB® software. After the processing of the images, the characteristics will be used for training and test of artificial neural net using the MLP algorithm, that will be a classifier of the same ones. The validation of the classifier will be made through statistical analysis of the correct and incorrect of the images.

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

GIMENEZ, Carolina Melleiro. Identification of bovines through recognition of images patterns of the muzzle using artificial neural nets. 2011. Master's Dissertation - Universidade de São Paulo (USP). Faculdade de Zootecnica e Engenharia de Alimentos (FZE/BT) Pirassununga.