Applications of artificial vision for quality monitoring of emerging foods

• Grant number: 23/07385-7
• Support Opportunities: Regular Research Grants
• Start date: February 01, 2024
• End date: January 31, 2026
• Field of knowledge: Agronomical Sciences - Food Science and Technology - Food Engineering
• Principal Investigator: Douglas Fernandes Barbin
• Grantee: Douglas Fernandes Barbin
• Host Institution: Faculdade de Engenharia de Alimentos (FEA). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated scholarship(s): 24/07881-7 - Application of low-cost NIR spectroscopy and near infrared hyperspectral imaging (NIR-HSI) and chemometrics for food safety inspection of samples relevant to Brazil and Mozambique., BP.PD

Abstract

Food security has become a major concern worldwide, leading to the development of new alternative foods. Quality control in the food industry is traditionally accomplished through chemical, physical and microbiological test. Some of these methods are slow, laborious and require chemicals producing residues. Nowadays it is possible to replace most of the drawbacks of these methods through indirect fast and non-destructive techniques. Hyperspectral imaging is currently the state of the art in this field, offering a number of advantages over traditional methods of quality assessment, including ease of adaptation for online systems and the possibility of simultaneous determination of several attributes. However, there are few studies on the subject in emerging countries. This project aims to strengthen the established research group on image analyses in the classification and evaluation of physical and chemical characteristics of food products, developing more sustainable, chemical free analytical methods of food products. The alternative foods intended for application include insect and oleogel as fat substitute. The combination of image analysis and NIR spectroscopy in hyperspectral imaging (HSI), may address major challenges in the food industry: (1) determination of composition of raw material, (2) identification of food adulteration and authentication and, (3) monitoring product quality. This technology has seen a reduction in equipment prices, but it could benefit from identification of specific wavelengths for new equipment dedicated to specific applications. However, it is necessary powerful mathematical and statistical tools to be able to analyse the large amount of multivariate information that is obtained. Artificial intelligence offers tools to extract information (data mining) from a raw data set and/or to calibrate models (machine learning) for predictive purposes. The analytical methodologies developed within the project would offer a reliable and accessible tool for industries and start-ups that are beginning to grow in this area of alternative foods and other applications. Since there is little information regarding the application of HSI for the study of these products, the new knowledge acquired will be of great scientific value. (AU)

Scientific publications

(4)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

MORAES, INGRID A.; KAUFMANN, KARINE CRISTINE; BARBON JUNIOR, SYLVIO; NEVES, MARINA G.; VILLA, JAVIER E. L.; BARBIN, DOUGLAS F.. Authentication of coriander oil and adulterant identification using electronic nose and spectroscopic techniques. Food Chemistry, v. 483, p. 10-pg., 2025-08-15. (23/16840-0, 19/03812-2, 23/07385-7, 24/15243-0)

MORAES, INGRID ALVES DE; ARRIGHI, LEONARDO; BARBON JR, SYLVIO; VILLA, JAVIER E. L.; CUNHA, ROSIANE LOPES; BARBIN, DOUGLAS FERNANDES. Explainable artificial intelligence (xAI) applied to deep computer vision of microscopy imaging and spectroscopy for assessment of oleogel stability over storage. Journal of Food Engineering, v. 394, p. 12-pg., 2025-07-01. (23/07385-7)

DE MORAES, INGRID ALVES; BARBON JUNIOR, SYLVIO; BARBIN, DOUGLAS FERNANDES. Interpretation and explanation of computer vision classification of carambola ( Averrhoa carambola L. ) according to maturity stage. Food Research International, v. 192, p. 10-pg., 2024-07-31. (19/27354-3, 23/07385-7, 15/24351-2)

MORAES, INGRID A.; BARBON JUNIOR, SYLVIO BARBON; VILLA, JAVIER E. L.; CUNHA, ROSIANE L.; BARBIN, DOUGLAS F.. Predicting oleogels properties using non-invasive spectroscopic techniques and machine learning. Food Research International, v. 207, p. 15-pg., 2025-04-25. (19/03812-2, 19/27354-3, 23/07385-7)