Semantic Segmentation Using Convolutional Neural Networks for Volume Estimation of Native Potatoes at High Speed

Miguel Chicchón; Ronny Huerta

doi:10.1007/978-3-030-76228-5_17

Semantic Segmentation Using Convolutional Neural Networks for Volume Estimation of Native Potatoes at High Speed

Miguel Chicchón
, Ronny Huerta

Research output: Chapter in Book/Report › Conference contribution › peer-review

1 Scopus citations

Abstract

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.

Original language	American English
Title of host publication	Information Management and Big Data - 7th Annual International Conference, SIMBig 2020, Proceedings
Editors	Juan Antonio Lossio-Ventura, Jorge Carlos Valverde-Rebaza, Eduardo Díaz, Hugo Alatrista-Salas
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	236-249
Number of pages	14
ISBN (Print)	9783030762278
DOIs	https://doi.org/10.1007/978-3-030-76228-5_17
State	Indexed - 2021
Externally published	Yes
Event	7th Annual International Conference on Information Management and Big Data, SIMBig 2020 - Virtual, Online Duration: 1 Oct 2020 → 3 Oct 2020

Publication series

Name	Communications in Computer and Information Science
Volume	1410 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	7th Annual International Conference on Information Management and Big Data, SIMBig 2020
City	Virtual, Online
Period	1/10/20 → 3/10/20

Bibliographical note

Publisher Copyright:
© 2021, Springer Nature Switzerland AG.

Keywords

Convolutional neural network
SegNet
Semantic segmentation
Transfer learning

Access to Document

10.1007/978-3-030-76228-5_17

Cite this

Chicchón, M., & Huerta, R. (2021). Semantic Segmentation Using Convolutional Neural Networks for Volume Estimation of Native Potatoes at High Speed. In J. A. Lossio-Ventura, J. C. Valverde-Rebaza, E. Díaz, & H. Alatrista-Salas (Eds.), Information Management and Big Data - 7th Annual International Conference, SIMBig 2020, Proceedings (pp. 236-249). (Communications in Computer and Information Science; Vol. 1410 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-76228-5_17

Chicchón, Miguel ; Huerta, Ronny. / Semantic Segmentation Using Convolutional Neural Networks for Volume Estimation of Native Potatoes at High Speed. Information Management and Big Data - 7th Annual International Conference, SIMBig 2020, Proceedings. editor / Juan Antonio Lossio-Ventura ; Jorge Carlos Valverde-Rebaza ; Eduardo Díaz ; Hugo Alatrista-Salas. Springer Science and Business Media Deutschland GmbH, 2021. pp. 236-249 (Communications in Computer and Information Science).

@inproceedings{126780c3192e42eea68e403997cd8da2,

title = "Semantic Segmentation Using Convolutional Neural Networks for Volume Estimation of Native Potatoes at High Speed",

abstract = "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.",

keywords = "Convolutional neural network, SegNet, Semantic segmentation, Transfer learning",

author = "Miguel Chicch{\'o}n and Ronny Huerta",

note = "Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG.; 7th Annual International Conference on Information Management and Big Data, SIMBig 2020 ; Conference date: 01-10-2020 Through 03-10-2020",

year = "2021",

doi = "10.1007/978-3-030-76228-5\_17",

language = "American English",

isbn = "9783030762278",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "236--249",

editor = "Lossio-Ventura, \{Juan Antonio\} and Valverde-Rebaza, \{Jorge Carlos\} and Eduardo D{\'i}az and Hugo Alatrista-Salas",

booktitle = "Information Management and Big Data - 7th Annual International Conference, SIMBig 2020, Proceedings",

address = "Germany",

}

Chicchón, M & Huerta, R 2021, Semantic Segmentation Using Convolutional Neural Networks for Volume Estimation of Native Potatoes at High Speed. in JA Lossio-Ventura, JC Valverde-Rebaza, E Díaz & H Alatrista-Salas (eds), Information Management and Big Data - 7th Annual International Conference, SIMBig 2020, Proceedings. Communications in Computer and Information Science, vol. 1410 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 236-249, 7th Annual International Conference on Information Management and Big Data, SIMBig 2020, Virtual, Online, 1/10/20. https://doi.org/10.1007/978-3-030-76228-5_17

Semantic Segmentation Using Convolutional Neural Networks for Volume Estimation of Native Potatoes at High Speed. / Chicchón, Miguel; Huerta, Ronny.
Information Management and Big Data - 7th Annual International Conference, SIMBig 2020, Proceedings. ed. / Juan Antonio Lossio-Ventura; Jorge Carlos Valverde-Rebaza; Eduardo Díaz; Hugo Alatrista-Salas. Springer Science and Business Media Deutschland GmbH, 2021. p. 236-249 (Communications in Computer and Information Science; Vol. 1410 CCIS).

Research output: Chapter in Book/Report › Conference contribution › peer-review

TY - GEN

T1 - Semantic Segmentation Using Convolutional Neural Networks for Volume Estimation of Native Potatoes at High Speed

AU - Chicchón, Miguel

AU - Huerta, Ronny

PY - 2021

Y1 - 2021

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://www.scopus.com/pages/publications/85111130152

U2 - 10.1007/978-3-030-76228-5_17

DO - 10.1007/978-3-030-76228-5_17

M3 - Conference contribution

AN - SCOPUS:85111130152

SN - 9783030762278

T3 - Communications in Computer and Information Science

SP - 236

EP - 249

BT - Information Management and Big Data - 7th Annual International Conference, SIMBig 2020, Proceedings

A2 - Lossio-Ventura, Juan Antonio

A2 - Valverde-Rebaza, Jorge Carlos

A2 - Díaz, Eduardo

A2 - Alatrista-Salas, Hugo

PB - Springer Science and Business Media Deutschland GmbH

T2 - 7th Annual International Conference on Information Management and Big Data, SIMBig 2020

Y2 - 1 October 2020 through 3 October 2020

ER -

Chicchón M, Huerta R. Semantic Segmentation Using Convolutional Neural Networks for Volume Estimation of Native Potatoes at High Speed. In Lossio-Ventura JA, Valverde-Rebaza JC, Díaz E, Alatrista-Salas H, editors, Information Management and Big Data - 7th Annual International Conference, SIMBig 2020, Proceedings. Springer Science and Business Media Deutschland GmbH. 2021. p. 236-249. (Communications in Computer and Information Science). doi: 10.1007/978-3-030-76228-5_17