ABSTRACT
Checking the quality of agricultural produce at every step of its supply chain is the need of the hour to reduce food wastage. Manual checking of food quality at every step can be inconsistent and time consuming. Automation of food quality detection, using non-invasive imagery based techniques, needs availability of ample amount of annotated data to train models. Collecting such data in large quantity in a controlled lab setting is an expensive affair. More-over, providing a point solution for every individual food item by training food item specific models is an impractical solution. Thus, there is a need for a mechanism which would capture the common meta-level visual degradation properties across a set of food items belonging to a specific category and use this meta-knowledge to predict the quality of a new food item belonging to that category with a paucity of training data. To address this challenge, as a part of the preliminary work, we conduct an initial set of experiments to demonstrate the applicability of existing Model Agnostic Meta-Learning (MAML) algorithm for fruit freshness detection task. The results indicate that for such a task, meta-learning can serve to be a more generic and efficient solution than using few-shot transfer-learning technique and traditional ML based approaches requiring explicit feature engineering.
- NajahMAl-Mhanna, Holger Huebner, and Rainer Buchholz. 2018. Analysis of the sugar content in food products by using gas chromatography mass spectrometry and enzymatic methods. Foods 7, 11 (2018), 185.Google ScholarCross Ref
- A Anushya. 2020. Quality recognition of banana images using classifiers. Int J Comput Sci Mob Comput 9, 1 (2020), 100--106.Google Scholar
- Sébastien MR Arnold, Praateek Mahajan, Debajyoti Datta, Ian Bunner, and Konstantinos Saitas Zarkias. 2020. learn2learn: A library for meta-learning research. arXiv preprint arXiv:2008.12284 (2020).Google Scholar
- Swarnambiga Ayyachamy, Varghese Alex, Mahendra Khened, and Ganapathy Krishnamurthi. 2019. Medical image retrieval using Resnet-18. In Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications, Vol. 10954. International Society for Optics and Photonics, 1095410.Google Scholar
- Cornelius S Barry and James J Giovannoni. 2007. Ethylene and fruit ripening. Journal of Plant Growth Regulation 26, 2 (2007), 143--159.Google ScholarCross Ref
- F Cadet. 2014. Quantitative determination of sugar in fruits by different methods. Indian Journal of Chemistry (2014).Google Scholar
- Jacinth Nithya Devanesan, Alagusundaram Karuppiah, and CV Kavitha Abirami. 2011. Effect of storage temperatures, O2 concentrations and variety on respiration of mangoes. Journal of Agrobiology 28, 2 (2011), 119--128.Google ScholarCross Ref
- Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic metalearning for fast adaptation of deep networks. In International Conference on Machine Learning. PMLR, 1126--1135. Google ScholarDigital Library
- Mingjun Li, Pengmin Li, Fengwang Ma, Abhaya M Dandekar, and Lailiang Cheng. 2018. Sugar metabolism and accumulation in the fruit of transgenic apple trees with decreased sorbitol synthesis. Horticulture research 5, 1 (2018), 1--11.Google Scholar
- Anusha Nagabandi, Ignasi Clavera, Simin Liu, Ronald S Fearing, Pieter Abbeel, Sergey Levine, and Chelsea Finn. 2019. Learning to adapt in dynamic, real-world environments through meta-reinforcement learning. Proceedings of International Conference on Learning Representations (ICLR) (2019).Google Scholar
- Mihai Oltean. 2018. Fruits 360 dataset. Mendeley Data (2018).Google Scholar
- Brian Rivera. [n.d.]. Fast Analysis of Sucrose, Glucose, and Fructose Composition in Fruit Juices and Processed Beverages using Simplified HPLC Methodology. ([n. d.]).Google Scholar
- Sirithon Siriamornpun and Niwat Kaewseejan. 2017. Quality, bioactive compounds and antioxidant capacity of selected climacteric fruits with relation to their maturity. Scientia Horticulturae 221 (2017), 33--42.Google ScholarCross Ref
- Satyam Srivastava, Sachin Boyat, and Shashikant Sadistap. 2014. A novel vision sensing system for tomato quality detection. International journal of food science 2014 (2014).Google ScholarCross Ref
Index Terms
- A Generic Few-Shot Solution for Food Shelf-Life Prediction using Meta-Learning
Recommendations
Few-shot Food Recognition via Multi-view Representation Learning
This article considers the problem of few-shot learning for food recognition. Automatic food recognition can support various applications, e.g., dietary assessment and food journaling. Most existing works focus on food recognition with large numbers of ...
Unsupervised meta-learning for few-shot learning
Highlights- Unsupervised meta-learning that auto-constructs tasks from unlabeled data.
- ...
AbstractMeta-learning is an effective tool to address the few-shot learning problem, which requires new data to be classified considering only a few training examples. However, when used for classification, it requires large labeled datasets, ...
Can we improve meta-learning model in few-shot learning by aligning data distributions?
AbstractMeta-learning becomes a promising way to solve the few-shot learning problem in recent research. This paradigm mainly relies on hierarchical architecture and episodic training to achieve good generalization on the new learning task. ...
Comments