TY - JOUR
T1 - Semantic Segmentation Using Convolutional Neural Networks for Volume Estimation of Native Potatoes at High Speed
AU - Chicchón Apaza, Miguel Ángel
AU - Huerta, Ronny
N1 - Publisher Copyright:
© 2021, Springer Nature Switzerland AG.
PY - 2020
Y1 - 2020
N2 - Peru is one of the main producers of a wide variety of native potatoes in the world. Nevertheless, to achieve a competitive export of derived products is necessary to implement automation tasks in the production process. Nowadays, volume measurements of native potatoes are done manually, increasing production costs. To reduce these costs, a deep approach based on convolutional neural networks have been developed, tested, and evaluated, using a portable machine vision system to improve high-speed native potato volume estimations. The system was tested under different conditions and was able to detect volume with up to 90% of accuracy.
AB - Peru is one of the main producers of a wide variety of native potatoes in the world. Nevertheless, to achieve a competitive export of derived products is necessary to implement automation tasks in the production process. Nowadays, volume measurements of native potatoes are done manually, increasing production costs. To reduce these costs, a deep approach based on convolutional neural networks have been developed, tested, and evaluated, using a portable machine vision system to improve high-speed native potato volume estimations. The system was tested under different conditions and was able to detect volume with up to 90% of accuracy.
KW - Convolutional neural network
KW - SegNet
KW - Semantic segmentation
KW - Transfer learning
UR - https://hdl.handle.net/20.500.12724/13906
UR - http://www.scopus.com/inward/record.url?scp=85111130152&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/f732f914-7bca-3983-afb5-842d03d61e20/
U2 - https://doi.org/10.1007/978-3-030-76228-5_17
DO - https://doi.org/10.1007/978-3-030-76228-5_17
M3 - Article (Contribution to Journal)
SN - 1865-0937
SP - 236
EP - 249
JO - Communications in Computer and Information Science
JF - Communications in Computer and Information Science
ER -