home    about    browse    search    latest    help 
Login | Create Account

Recognition of inlet wet food in drying process through a deep learning approach

Moscetti, Roberto; Massaro, Simone; Chillemi, Giovanni; Sanna, Nico; Sturm, Barbara; Nallan Chakravatula, Swathi Sirisha and Massantini, Riccardo (2019) Recognition of inlet wet food in drying process through a deep learning approach. In: Proceedings of Eurodrying 2019, 10-12 July 2019, Torino, Italy.

[thumbnail of Eurodrying2019_full_paper_167_revision.pdf] PDF - Published Version - English
[thumbnail of Eurodrying_2019_v2.pdf] PDF - Presentation - English


Deep learning was tested for its feasibility as CV tool for the analysis of inlet wet food into the drying process. In detail, convolutional neural networks (CNNs) were successfully applied for addressing the following tasks: (i) the semantic image segmentation of the inlet product; (ii) the inlet product classification for automatic selection of drying parameters. As a result, CNNs have been shown to be used for the development of smart dryers able to monitor and control the process.

EPrint Type:Conference paper, poster, etc.
Type of presentation:Paper
Keywords:Python, Jupyter, artificial intelligence, machine learning, convolutional neural networks, SusOrgPlus
Subjects: Food systems > Food security, food quality and human health
Food systems > Processing, packaging and transportation
Research affiliation: European Union > CORE Organic Cofund > SusOrgPlus
Germany > University of Kassel > Department of Agricultural Engineering and Agricultural Engineering in the Tropics and Subtropics
Italy > Univ. Tuscia
Horizon Europe or H2020 Grant Agreement Number:727495
Related Links:https://projects.au.dk/coreorganiccofund/core-organic-cofund-projects/susorgplus/, https://www.susorgplus.eu/
Deposited By: Moscetti, Ass. Prof. Roberto
ID Code:36552
Deposited On:12 Nov 2019 09:09
Last Modified:29 Jan 2020 11:12
Document Language:English
Refereed:Peer-reviewed and accepted

Repository Staff Only: item control page


Downloads per month over past year

View more statistics