Cow Weight Estimation Using Local Adaptive Thresholding Method And Connected Component Labelling

DOI

10.2991/icst-18.2018.32How to use a DOI?

Keywords

Cow weight; Calibration; edge detection; connected component labeling

Abstract

The development of technology, information and communication provides a new alternative to predict cow weight through Image Processing. This study utilizes Image Processing in visualizing the measurement of Chest Circumference and cow body length automatically. The cow weight estimation are very dependent on cow image segmentation result. Image segmentation method used in this study is local adaptive thresholding combined with the Connected Component Labeling (CCL) method. The implementation of the Chest Circumference and Body Length endpoints in the foreground is converted into centimeters (cm) to ensure cow weight estimation can be calculated using the Lambourne formula. In this study, the accuracy of RMSE was obtained from the cow weight data taken at 150, 170 and 190 cm distance. The accuracy is 20.35, 30.77 and 23.33 respectively. This research can be contribution to development of local cattle farms in Indonesia

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Rosida Vivin Nahari
AU  - Novita Subagiarti
AU  - Achmad Jauhari
AU  - Riza Alfita
AU  - Kunto Aji Wibisono
AU  - Achmad Fiqhi Ibadillah
AU  - Mirza Pramudia
PY  - 2018/12
DA  - 2018/12
TI  - Cow Weight Estimation Using Local Adaptive Thresholding Method And Connected Component Labelling
BT  - Proceedings of the International Conference on Science and Technology (ICST 2018)
PB  - Atlantis Press
SP  - 148
EP  - 152
SN  - 2589-4943
UR  - https://doi.org/10.2991/icst-18.2018.32
DO  - 10.2991/icst-18.2018.32
ID  - Nahari2018/12
ER  -