25 September 1998 Neural network predicts carrot volume with only three images
Author Affiliations +
Proceedings Volume 3545, International Symposium on Multispectral Image Processing (ISMIP'98); (1998) https://doi.org/10.1117/12.323576
Event: International Symposium on Multispectral Image Processing, 1998, Wuhan, China
Abstract
A mechanism turned a vision camera around a fixed carrot taking 100 images of it. A 3D reconstruction finite element algorithm reproduced the volume using finite area triangles and morphological operations to optimize memory utilization. Volume from several carrots were calculated and correlated against real volume achieving a 98% success rate. Three images 120 degrees apart were acquired and the main features extracted. A neural network system was trained using the features, increasing the measuring speed and obtaining together with a regression algorithm an accuracy of 95% in predicting the real volume.
© (1998) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Federico Hahn, Federico Hahn, Sergio Sanchez, Sergio Sanchez, } "Neural network predicts carrot volume with only three images", Proc. SPIE 3545, International Symposium on Multispectral Image Processing (ISMIP'98), (25 September 1998); doi: 10.1117/12.323576; https://doi.org/10.1117/12.323576
PROCEEDINGS
4 PAGES


SHARE
Back to Top