| Home

Overview


Original Research

BODY CONDITION SCORE ESTIMATION USING SALIENT OBJECT AND CONVOLUTIONAL NEURAL NETWORK

A.SUMATHI 1, M.GERMANUS ALEX 2, and J.L.WALTER JEYAKUMAR 3

Vol 17, No 05 ( 2022 )   |  DOI: 10.5281/zenodo.6613367   |   Author Affiliation: Research Scholar, Department of Computer Science, St. Xavier’s college, (Autonomous), Palayamkottai-627002, Tirunelveli, affiliated to Manonmaniam Sundaranar University, Abishekapatti, Tirunelveli - 627 012, Tamil Nādu, India 1, Assistant Professor in Computer Science, Government Arts & Science College, Nagercoil, affiliated to Manonmaniam Sundaranar University, Abishekapatti, Tirunelveli - 627 012, Tamil Nadu, India 2, Associate Professor in Computer Science, St.Xavier’s College (Autonomous), Palayamkottai, Tirunelveli, affiliated to Manonmaniam Sundaranar University, Abishekapatti, Tirunelveli - 627 012, Tamil Nadu, India 3   |   Licensing: CC 4.0   |   Pg no: 377-389   |   To cite: A.SUMATHI, et al., (2022). BODY CONDITION SCORE ESTIMATION USING SALIENT OBJECT AND CONVOLUTIONAL NEURAL NETWORK. 17(05), 377–389. https://doi.org/10.5281/zenodo.6613367   |   Published on: 30-05-2022

Abstract

Every human life is associated with dairy products, especially milk. A cow is the root source of milk producers. Body Condition Score (BCS) is the method used to find the amount of amount of energy reserved by the cow. It is used to predict the cow's health. The objective of this paper is to automate the method of estimating BCS. This paper proposed an efficient method for estimating BCS using the salient object and Convolutional Neural Network. The cow's body is identified from the edge map from which the width is used as a feature. The edge map is given to CNN for another feature. These two features are combined and given to a regression technique for predicting BCS. The proposed method is evaluated on BCS dataset with 206 images. The performance of the proposed method is evaluated using the following metrics such as R2 ,Accuracy and Root Mean Square Error. The efficiency of the proposed method is justified by comparing the proposed method with the existing methods.


Keywords

Convolutional neural network, salient object, regression