Abstract— This work provides a combined method, based on Artificial Neural Networks (ANNs) and Machine Vision (MV) systems, with the aim of assess a real-time estimation of acidity level and of peroxides number of olive oil extracted by a continuous extraction process. These parameters may be accurately measured by means of a chemical analysis (CEE Rule no. 2568/91, G.U. CEE no. L 248, 1991). This analysis has to be performed in an equipped laboratory and does not permit to the operators (working in the oil mill) to have a real-time control of the quality of the extracted oil. The present work allows a straightforward approach for an accurate estimation of the qualitative parameters directly during the oil extraction process, thus allowing a quality control of the oil quality without the requirement of a time-expensive chemical analysis. The estimation is achieved both through the measurement of several agronomical and technological parameters commonly measured by the technicians working at the oil mills and by means of machine vision systems. Some of the parameters correlated to the sanitary condition of olives and to ripeness are evaluated by means of image processing algorithms. An ANN based algorithm is able to process the agronomical, technological and image data and gives, as output, a reliable estimation of peroxides and acidity. The results of the estimation achieved by the ANN based system have been compared with the results of the chemical analyses carried out by Florence Commerce Chamber “Laboratorio Chimico Merceologico—Azienda Speciale CCIAA di Firenze” according in force to European Union Rules standards. The system has been developed and tested on the oil mill “TEM Toscana Enologica Mori” of Florence, Italy where is actually running. The work has been financed by the Tuscany Regional Agricultural Development and Innovation Office (ARSIA: Azienda Regionale per lo Sviluppo e l’Innovazione dell’Agricoltura) and is a part of a 3-year project whose objective is to create an entirely software + hardware controlled oil mill.

Real-time estimation of peroxides and acidity level of extra-virgin olive oil: an integrated approach / M. Carfagni; R. Furferi; M. Daou. - In: INTERNATIONAL JOURNAL OF MATHEMATICS AND COMPUTERS IN SIMULATION. - ISSN 1998-0159. - STAMPA. - Issue 2 - Volume 2:(2008), pp. 206-214.

Real-time estimation of peroxides and acidity level of extra-virgin olive oil: an integrated approach

CARFAGNI, MONICA;FURFERI, ROCCO;DAOU, MARCO
2008

Abstract

Abstract— This work provides a combined method, based on Artificial Neural Networks (ANNs) and Machine Vision (MV) systems, with the aim of assess a real-time estimation of acidity level and of peroxides number of olive oil extracted by a continuous extraction process. These parameters may be accurately measured by means of a chemical analysis (CEE Rule no. 2568/91, G.U. CEE no. L 248, 1991). This analysis has to be performed in an equipped laboratory and does not permit to the operators (working in the oil mill) to have a real-time control of the quality of the extracted oil. The present work allows a straightforward approach for an accurate estimation of the qualitative parameters directly during the oil extraction process, thus allowing a quality control of the oil quality without the requirement of a time-expensive chemical analysis. The estimation is achieved both through the measurement of several agronomical and technological parameters commonly measured by the technicians working at the oil mills and by means of machine vision systems. Some of the parameters correlated to the sanitary condition of olives and to ripeness are evaluated by means of image processing algorithms. An ANN based algorithm is able to process the agronomical, technological and image data and gives, as output, a reliable estimation of peroxides and acidity. The results of the estimation achieved by the ANN based system have been compared with the results of the chemical analyses carried out by Florence Commerce Chamber “Laboratorio Chimico Merceologico—Azienda Speciale CCIAA di Firenze” according in force to European Union Rules standards. The system has been developed and tested on the oil mill “TEM Toscana Enologica Mori” of Florence, Italy where is actually running. The work has been financed by the Tuscany Regional Agricultural Development and Innovation Office (ARSIA: Azienda Regionale per lo Sviluppo e l’Innovazione dell’Agricoltura) and is a part of a 3-year project whose objective is to create an entirely software + hardware controlled oil mill.
2008
Issue 2 - Volume 2
206
214
M. Carfagni; R. Furferi; M. Daou
File in questo prodotto:
File Dimensione Formato  
Int. Journ. of Matematics and Computers in Simulation (2008)_SCOPUS.pdf

accesso aperto

Tipologia: Versione finale referata (Postprint, Accepted manuscript)
Licenza: Open Access
Dimensione 1.45 MB
Formato Adobe PDF
1.45 MB Adobe PDF

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/347025
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact