Generation of Simulated Dataset of Computed Tomography Images of Eggs and Extraction of Measurements Using Deep Learning
Jean Pierre Brik López Vargas, Davi Duarte de Paula, Denis H. P. Salvadeo, Emílio Bergamim · 2024
This paper extracts morphometric measurements of the different volumes of chicken egg components (shell, yolk, albumen and air chamber) by evaluating the segmentation algorithms, U-Net and Fully Convolutional Network (FCN).It also presents a new data set of 3D CT images of chicken eggs, simulating the different densities of a real one in the Digital Imaging and Communications in Medicine (DICOM) format and its labeled masks.The 3D models trained end-to-end showed high generalization even in the presence of variations in egg size and internal structures, achieving state-of-the-art segmentation performance with 99.4% accuracy.