Memorias de investigación
Communications at congresses:
Monitoring Watercress Shelf-life with VNIR Hyperspectral Image through Packaging Film

Research Areas
  • Food preserving,
  • Horticulture

The aim of the present work is to monitor the shelf-life of watercress (Nasturtium officinale) by means of hyperspectral images through packaging films. Fifteen watercress leaves were randomly selected from a commercial bag, put inside Petri dishes covered by plastic film and stored at 4ºC for 16 days. Hyperspectral images (VNIR 400-1000 nm) were taken during this storage, getting five acquisitions for each leaf. The average spectrum of each image was computed; several models were obtained from these average spectra. A radiometric correction was applied in order to avoid the variation in transmittance of the plastic film along storage in the hyperspectral images. Afterwards, three spectral pre-processing procedures (no preprocess, Savitsky?Golay and Standard Normal Variate, combined with Principal Component Analysis) were applied to obtain different models. These specific models for watercress along with other models previously developed for spinach were applied and compared. The artificial images of scores obtained, applying each model to the original and complete images, were compared by means of Analysis of Variance and Wilks-?. Radiometric correction allowed the supervision of shelf-life in leafy vegetables through commercial transparent films. All models applied were able to monitor the aging of the leaves. However, the models developed specifically for watercress spectra were more suitable for monitoring the shelf-life of this vegetable leaf along the storage. There were some differences between the models applied for spinach and for watercress leaves. Despite it, it seems to be necessary to study the spectra of each leafy vegetable independently for developing prediction models more able to monitor the aging of the leaves. Hyperspectral imaging could be used for monitoring the freshness of watercress and/or mix of salad leaves during their shelf-life. Multispectral indexes based on results of PCA and spectral patterns, could contribute to the transference of the technique to the industry.
EuroAgeng 2018
Start Date
End Date
From page
To page
Ageng 2018 Proceeding. New Engineering Concepts for Valued Agriculture

Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: LPF-TAGRALIA: Técnicas Avanzadas en Agroalimentación
  • Departamento: Ingeniería Agroforestal