A method to estimate Grape Phenolic Maturity based on seed images

Avila, Felipe; Mora, Marco; Fredes, Claudio

doi:10.1016/j.compag.2013.12.006

Cited by 18 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An alternative to this subjective, human observation of seeds was proposed by Rodríguez-Pulido et al (2012b), who automated the colour assignment of the Vitis vinifera seeds by incorporating computer vision techniques. Nevertheless, this technology has not yet been capable of detecting any colour differences in lapses shorter than a month during ripening (Ávila et al, 2014;Rodríguez-Pulido et al 2012b). Furthermore, computer vision technology requires some very expensive hardware, such as cameras with a diffuse-light anti-shadow chamber, as well as specific software to define the representative seed colour (Rodríguez-Pulido et al, 2012b).…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, computer vision technology requires some very expensive hardware, such as cameras with a diffuse-light anti-shadow chamber, as well as specific software to define the representative seed colour (Rodríguez-Pulido et al, 2012b). A recent series of studies developed at the Universidad Catolica del Maule (Chile) (Ávila et al, 2014;Oyarce, 2014;Zuñiga et al, 2014;Ávila et al, 2015) proposed a simple computing methodology to capture images with a simple scanner and a digital seed colour scale to define seed colours by image treatment and pattern recognition (Gevers & Smeulders, 1999). However, this methodology has not yet been associated with the chemical parameters usually employed in assessing grape ripening.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Analysis of Seed Colour During Ripening of Cabernet Sauvignon Grapes

Fredes

Mora

Carrasco-Benavides

2017

SAJEV

View full text Add to dashboard Cite

This case study examines seed colour during ripening using an exhaustive colorimetric analysis. The aim was to associate the chemical ripening with the seed colour in order to estimate the ripening stages of Cabernet Sauvignon grapes. Cluster samples, obtained from a vertical shoot-positioned vineyard in central Chile, were monitored for their technological and phenolic maturity, as well as for the colorimetric and chemical characteristics of the seeds. The colours of the scanned seed images were determined by human as well as by computer vision. In the first case, an expert assigned a colour to each seed part. In the second case, a computer program estimated the colours of the scanned seed images. An exhaustive analysis of seed colour was proposed, instead of a general observation of seed browning. The seed colour presented a wide range of colours, from moss green to dark brown, depending on the maturity and the face observed. The ripening stages identified, along with the chemical and colorimetric information gathered, were under ripe seed (brown with green traces), ripe seed (dark brown with green traces) and overripe seed (dark brown without any green traces). A new way to quantify seed colour is shown in this paper.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Analysis of Seed Colour During Ripening of Cabernet Sauvignon Grapes

Fredes

Mora

Carrasco-Benavides

2017

SAJEV

View full text Add to dashboard Cite

show abstract

“…The removal of distractors, such as peduncles and skin-attached imperfections, was performed without deforming the curvature of the objects [11,12] (Figure 2). Segmentation of the images from the bottom was performed with the c1c2c3 model in c3 channel, as proposed [19]. Figure 3 shows a histogram in the c3 channel olive trays, highlighting the classifying power based on the color of the olives [13].…”

Section: Treatment Images and Spectrum Of Olivesmentioning

confidence: 99%

A Model Based on Clusters of Similar Color and NIR to Estimate Oil Content of Single Olives

Fredes

Valero

Diezma

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

The color and NIR spectrum are key to build an oil estimation model, thus it requires individual olives clustering before the Sohlext oil extraction method can be applied. The objective was to analyze an OC estimation model of individual olives, based on cluster of similar color and NIR spectrum in different combination of the first and/or the second season. This study was performed with Chilean Arbequina olives in 2016 and 2017. The descriptor of the cluster consisted of the 3 color channels of c1, c2, c3 color model plus 11 reflectance points between 1710 and 1735 nm of each olive, normalized with the Z-score index. Clusters of similar color and NIR spectrum were formed with the k-means++ algorithm, leaving a sufficient amount of olives to be able to perform the Sohlext analysis of OC, as reference value. The estimation models were based on the Support Vector Machine. The test was carried out with the Leave One-Out Cross Validation in different training-testing combinations. The best model predicted the OC with 6% and 13%deviation respect to the real value in one season by itself and when one season tested with another season, respectively. The use of clustering in estimation model is discussed.

show abstract

“…The data set contains 289 images from grape seeds acquired using a conventional scanner (Canon MG-3110), obtained between February and May 2013 (For a complete description of the dataset, the reader is referred to [5]). From Figures 1(a), (b) and (c) we can appreciate the color difference for the different ripeness stages.…”

Section: Methodsmentioning

confidence: 99%

“…Discriminant analysis was used to determine whether a sample belongs to any class. A similar approach was taken in [5], where grape seeds are classified into mature or in-mature classes by means of a neural network classifier. Later in [6], the center of mass of the color histogram was proposed as a feature for the fruit maturity classification task.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Learning for Ripeness Estimation From Grape Seeds Images

Hernández

Morales

Urrutia

2017

International Journal on Smart Sensing and Intelligent Systems

View full text Add to dashboard Cite

Abstract-Estimating the current stage of grape ripeness is a crucial step in wine making and becomes especially important during harvesting. Visual inspection of grape seeds is one method to achieve this goal without performing chemical analysis, however this method is prone to failure. In this paper, we propose an unsupervised visual inspection system for grape ripeness estimation using the Dirichlet Mixture Model (DMM). Experimental analysis using real world data demonstrates that our approach can be used to estimate different ripeness stages from unlabeled grape seeds catalogs.

show abstract

A method to estimate Grape Phenolic Maturity based on seed images

Cited by 18 publications

References 10 publications

An Analysis of Seed Colour During Ripening of Cabernet Sauvignon Grapes

An Analysis of Seed Colour During Ripening of Cabernet Sauvignon Grapes

A Model Based on Clusters of Similar Color and NIR to Estimate Oil Content of Single Olives

Unsupervised Learning for Ripeness Estimation From Grape Seeds Images

Contact Info

Product

Resources

About