An open-access computer image analysis (CIA) method to predict meat and fat content from an android smartphone-derived picture of the bovine 5th-6th rib.

Abstract

Marbling and rib composition are important attributes related to carcass yields and values, beef quality, consumer satisfaction and purchasing decisions. An open-access computer image analysis method based on a fresh beef rib image captured under nonstandardized and uncontrolled conditions was developed to determine the intramuscular, intermuscular and total fat content. For this purpose, cross-section images of the 5th-6th rib from 130 bovine carcasses were captured with a Galaxy S8 smartphone. The pictures were analyzed with a program developed using ImageJ open source software. The 17 processed image features that were obtained were mined relative to gold standard measures, namely, intermuscular fat, total fat and muscles dissected from a rib and weighed, and intramuscular fat content (IMF - marbling) determined by the Soxhlet method. The best predictions with the lowest prediction errors were obtained by the sparse partial least squares method for both IMF percent and rib composition and from a combination of animal and image analysis features captured from the caudal face of the 6th rib captured on a table. These predictions were more accurate than those based on animal and image analysis features captured from the caudal face of the 5th rib on hanging carcasses. The external-validated prediction precision was 90% for IMF and ranged from 71 to 86% for the total fat, intermuscular and muscle rib weight ratios. Therefore, an easy, low-cost, user-friendly and rapid method based on a smartphone picture from the 6th rib of bovine carcasses provides an accurate method for fat content determination.