Multispectral images of peach related to firmness and maturity at harvest

Lleó, L.; Elorza, Pilar Barreiro; Ruiz-Altisent, Margarita; Herrero, A.

doi:10.1016/j.jfoodeng.2009.01.028

Cited by 82 publications

(48 citation statements)

References 33 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As an advantage to other classiflcation methods, Ward's method takes into account all histograms of the data set at every level of the grouping, producing very well structured and homogeneous groups (Otto, 2007). Besides, this method gave rise to successful results in previous works investigating fruit ripeness (Lleó et al, 2009;Herrero et al, 2011). AMatLab® devoted code was developed in order to genérate groups automatically on the basis of the input máximum Ward linkage distance, which is derived from the analysis of the cluster tree features.…”

Section: Non-supervised Image Classiflcationmentioning

confidence: 99%

A multispectral vision system to evaluate enzymatic browning in fresh-cut apple slices

Lunadei

Galleguillos

Diezma

et al. 2011

Postharvest Biology and Technology

View full text Add to dashboard Cite

Keywords:Fresh-cut apples Enzymatic browning CIÉ L*a*f>* color space Multispectral images Image analysisThe main objective of this study was to develop a visión system that is able to classify fresh-cut apple slices according to the development of enzymatic browning. The experiment was carried out on 'Granny Smith' apple slices stored at 7.5 °C for 9 days (n = 120). Twenty-four samples were analyzed per day: at zero time and after storage for 1, 3, 7 and 9 days, which corresponds to treatments to, ti, h, ti and t% respectively. Multispectral images were acquired from the samples by employing a 3-CCD camera centered at the infrared (IR, 800nm), red (R, 680nm) and blue (B, 450nm) wavelengths. Apple slices were evaluated visually according to a visual color scale of 1 -5 (where 1 corresponds to fresh samples without any browning and 5 to samples with severe discoloration), to obtain a sensory evaluation Índex (¡SE) for each sample. Finally, for each sample and for each treatment, visible (VIS) relative reflectance spectra (360-740 nm) were obtained. In order to identify the most related wavelengths to enzymatic browning evolution, unsupervised pattern recognition analysis of VIS reflectance spectra was performed by principal components analysis (PCA) on the autoscaled data. Máximum loading valúes corresponding to the B and R áreas were observed. Therefore, a classification procedure was applied to the relative histograms of the following monochromatic images (virtual images), which were computed pixel by pixel: (R-B)/(R + B),R-B and B/R. Inall cases,a non-supervised classification procedure was able to genérate three image-based browningreference classes (BRC): Cluster A (corresponding to the to samples), ClusterB (ti andt3 samples) and Cluster C(t7 and tg samples). Aninternal and anexternal validation (n = 120) were carried out, and the best classifications were obtained with the (R -B)/(R + B) and B/R image histograms (internal validation: 99.2% of samples correctly classified for both virtual images; external validation: 84% with (R -B)/(R + B) and 81% with B/R). The camera classification was evaluated according to the colorimetric measurements, which were usually utilized to evalúate enzymatic browning development (CIÉ L'a'b* color parameters and browning Índex, BI) and according to ¡SE-For both validation phases a*, b*, BI and ¡SE increased while I* valúes decreased with image-based class number, thereby reflecting their browning state.

show abstract

Section: Non-supervised Image Classiflcationmentioning

confidence: 99%

A multispectral vision system to evaluate enzymatic browning in fresh-cut apple slices

Lunadei

Galleguillos

Diezma

et al. 2011

Postharvest Biology and Technology

View full text Add to dashboard Cite

show abstract

“…The present research proposes two new indexes, Indi and Ind 2 , to be compared with two previously used indexes, Ind 3 (Lleó et al, 2009;Sims and Gamón, 2002) and IAD (Ziosi et al, 2008). All of these indexes were extracted from hyperspectral images, and their corresponding multispectral images were computed.…”

Section: Discussionmentioning

confidence: 99%

“…This phenomenon did not occur with red tomatoes, which were the ripest. Lleó et al (2009) studied the behaviour of peach images acquired at 680 nm that covered the whole surface of the fruit. As the fruit ripens, the reflection in this band increases due to chlorophyll degradation.…”

Section: State Ofthe Artmentioning

confidence: 99%

“…Both wavelengths are related to the NDVI index because they are in the middle of the broad bands typically used in NDVI. Classification algorithms have been proposed based on red (675 nm) divided by infra-red (800 nm) images based on non-supervised clustering (Ward, 1963) whilst gathering the whole variability of ripeness in the harvest and post-harvest chain (Lleó et al, 2009). This classification presented a parallel evolution with firmness.…”

Section: State Ofthe Artmentioning

confidence: 99%

“…(a) Indi = (R 730 + R 6 4o) -2 * R 6 so (b) Ind 2 = JW(R 6 4o + Riso) (c) Ind 3 = RsislR&oo (d) I AD = loglO(R 720 /R 6 7o) Indi and Ind 2 are the new indexes, and the other two were employed before; Ind 3 was proposed by Sims and Gamón (2002) and Lleó et al (2009), and I A D was proposed by Ziosi et al (2008). An artificial image of each Índex was obtained computing the corresponding reflectance images.…”

Section: Images Computed Based On Chlorophyll Indexesmentioning

confidence: 99%

See 2 more Smart Citations

Comparison of multispectral indexes extracted from hyperspectral images for the assessment of fruit ripening

Lleó

Roger²,

Herrero-Langreo

et al. 2011

Journal of Food Engineering

Self Cite

View full text Add to dashboard Cite

Keywords:Hyperspectral imaging Vision Ripeness Non-destructive assessment Quality PeachThe present research is focused on the application of artificial visión to assess the ripening of red skinned soft-flesh peach ('Richlady'). Artificial visión allows a spatially detailed determination of the ripening stage of the fruit. The considered optical indexes (Indi and Ind2, proposed in the present research, and Ind 3 and I AD , proposed by other authors) are based on the combination of wavelengths cióse to the chlorophyll absorption peak at 680 nm. Ind} corresponds approximately to the depth of the absorption peak, and Ind 2 corresponds to the relative absorption peak. An artificial image of each Índex was obtained by computing the corresponding reflectance images, which were acquired with a hyperspectral camera. All indexes were able to correct convexity (except for the just-harvested peaches and for Ind}). Ind 2 is the preferred Índex; it showed the highest discriminating power between ripening stages and no influence of convexity. Ind 2 also allowed the differentiation of ripening regions within the fruits, and it showed the evolution of those regions during ripening.

show abstract

Rapid and non‐destructive determination of rancidity levels in butter cookies by multi‐spectral imaging

Xia

Liu

et al. 2015

J Sci Food Agric

View full text Add to dashboard Cite

show abstract

Multispectral images of peach related to firmness and maturity at harvest

Cited by 82 publications

References 33 publications

A multispectral vision system to evaluate enzymatic browning in fresh-cut apple slices

A multispectral vision system to evaluate enzymatic browning in fresh-cut apple slices

Comparison of multispectral indexes extracted from hyperspectral images for the assessment of fruit ripening

Rapid and non‐destructive determination of rancidity levels in butter cookies by multi‐spectral imaging

Contact Info

Product

Resources

About