Support System for Decision Making through Phenotypic Evaluation of Brown Swiss Cattle

Authors

  • Hugo Alatrista-Salas Universidad del Pacífico
  • Julianna Milagros Apumayta Lopez Pontificia Universidad Católica del Perú
  • Eduardo Leuman Fuentes Navarro Universidad Nacional Agraria la Molina https://orcid.org/0000-0001-9351-9853
  • Miguel Nunez-del-Prado Universidad del Pacífico

Keywords:

Object detection, Tensor Flow, Brown Swiss, MobileNet

Abstract

Phenotypic evaluation of Brown Swiss cows is a method  used in the Peruvian Andean Region to identify and select breeding females. Selection is based on their closeness to ideal dairy conformation. This task is perform by a specialists in stock judging. Under this context, the aim of the present study was to demonstrate the feasibility to perform a partial phenotypic evaluation of Brown Swiss cows  by overlapping templates through development of a cow detection model and a  decision making support system for identification and automatic classification of Brown Swiss cattle. TensorFlow Object Detection API was used to detect the cow in real time. The learning transfer approach was used for training, and MobilNet was selected as a pre-trained architecture. The results were reflected in the development of a mobile app, which can determine, through the automatic adjustment and calibration of the template on the cow, whether an animal has Brown Swiss breed phenotypic characteristics.

Published

2020-10-06
Bookmark and Share