Smart Solutions to Prevent Food Waste, with Special Focus on Fruits and Vegetables (F&V) Lose and Waste (L&W)
The United Nations fixed 17 Global Sustainable Development goals (SDG @https://sdgs.un.org/goals) to be reached by 2030. Goal no. 2 is “Zero Hunger”, and target 12.3 of SDG no. 12 is to “halve food waste at the retail and consumer level” with the aim of increasing the amount of food in the world and meeting the needs of population growth.
In parallel, new developments in Machine Learning (ML), Deep Learning (DL) and Computer Vision (CV) allow the design and implementation of smart systems capable of supporting humans to tackle this challenge. This special session aims to bring together the latest research on automatic food classification systems, designed for waste quantification and management. Also, this is a call for improved algorithms for segmentation of food images, as necessary pre-processing steps to allow classification. Moreover, special attention is given to smart systems capable of assessing the level of healthiness and/or freshness of fruits and vegetables (F&V). Improved classification algorithms capable of recognizing the quality of F&V could be implemented in several automated systems, ranging from smart containers to intelligent fridges and shelves at the supermarkets. To date, humans are mainly involved in this process by scanning every item, but this procedure is time-consuming, expensive, and error prone. Automatic systems could be more effective, also because working 24/7.
Furthermore, original technologies and/or new solutions, such electronic noise, the use of multi-spectral or hyper-spectral lights for monitoring systems, sensors and algorithms to reduce food loss and waste (FLW) during processing, transportation, conservation, distribution and retail, are also welcome. Finally, since the current research in this field is limited by the lack of publicly available databases, this special session welcomes also papers introducing to the research community new and large collections of images, which must be well documented and supported by benchmark algorithms.
Related topics include but are not limited
to:
● Automatic (food) classification
systems
● Semantic/instance segmentation
● Adversarial Defense
● Food waste quantification
● Smart systems to monitor the level of freshness and/or healthiness
of fruits and/or vegetables
● Smart systems for automatic disease classification
● Disease severity estimation in plant infection
● Prediction of disease progression in plants’ leaves
● Original technologies and/or new solutions to reduce FLW
● Release of new and large databases to monitor the level of
freshness and/or healthiness of fruits and/or vegetables
● Release of new and large databases for FLW
Chairman: Dr. Elena Battini Sonmez, Istanbul Bilgi University, Turkey (E-mail: ebsonmez@bilgi.edu.tr)
Bio: Elena Battini Sönmez (EBS) works as Assoc. Prof. in the Department of Computer Engineering at İstanbul Bilgi University. EBS received her B.S. degree in Computer Science from Pisa University, Italy, her M.S. degree in Computing Software and System Design from the University of Newcastle upon Tyne, UK, and her Ph.D. degree in Computer Engineering from Yildiz Teknik University, TR. EBS is an active member of the COST project CA22134 with title “Sustainable Network for agrifood loss and waste prevention, management, quantification and valorization (FoodWaStop)”. Her research interests include digital image processing, machine learning, artificial intelligence, human-robot interaction, and affective computing.