A novel beef marbling score estimation algorithm is proposed in this work. We develop a marbling score estimation network (MSENet), which simultaneously performs marbling score estimation and eye muscle area segmentation. The proposed MSENet includes a segmentation module, a bridge block, and a marbling scoring module. The segmentation module segments out eye muscle area from input images and the scoring module estimates marbling scores of input beef images. The proposed bridge block conveys the segmentation information for eye muscle area from the segmentation module to the scoring module. MSENet is trained on a new large-scale beef image dataset (more than 10,000), called the Hanwoo dataset. Experimental results demonstrate that the proposed MSENet achieves the reliable score estimation performance on the Hanwoo Dataset and the proposed bridge block effectively improves the estimation accuracy (Pearson's correlation coefficient: 0.952, Mean absolute error: 0.543).
Keywords: Automated beef grading system; Beef marbling; Computer vision; Convolutional neural networks; Deep learning.
Copyright © 2022 Elsevier Ltd. All rights reserved.