Applying data mining and Computer Vision Techniques to MRI to estimate quality traits in Iberian hams

Pérez‐Palacios, Trinidad; Caballero, Daniel; Caro, Andrés; Rodríguez, Pilar Vega; Antequera, Teresa

doi:10.1016/j.jfoodeng.2014.01.015

Cited by 54 publications

(29 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Previous studies have also showed the goodness of these techniques for predicting sensory Table 3 Prediction equations, correlation coefficient (R 2 ) and MAE of salt content in the S and B muscles at EPS stage of the Iberian ham processing as a function of computational textures feature of each method individually and all together (A, B, C, D traits and the content of lipids in Iberian hams (Caro et al, 2003;P erez-Palacios et al, 2010bP erez-Palacios et al, , 2014.…”

Section: Predictionmentioning

confidence: 99%

Modeling salt diffusion in Iberian ham by applying MRI and data mining

Caballero

Caro

Rodríguez

et al. 2016

Journal of Food Engineering

Self Cite

View full text Add to dashboard Cite

Section: Predictionmentioning

confidence: 99%

Modeling salt diffusion in Iberian ham by applying MRI and data mining

Caballero

Caro

Rodríguez

et al. 2016

Journal of Food Engineering

Self Cite

View full text Add to dashboard Cite

“…Considering the data mining techniques, MLR and DT are appropriate, respectively, to deduce physico-chemical parameters of hams [10], and to classify as a function of salt content in hams [11]. Regarding to the predictive technique, MLR allows obtaining equations to determine the physico-chemical characteristics and sensory attributes of Iberian hams [12] and loins [13][14][15] with a high degree of reliability, and analysing the quality of these meat products in a non-destructive, efficient, effective and accurate way.…”

Section: Brief Resultsmentioning

confidence: 99%

“…Databases were constructed with all these data. Different data mining techniques were applied on them: deductive (MLR) [10], classification (DT and RBS) [11] and prediction techniques (IR and MLR) [12][13][14][15].…”

Section: Brief Methodsmentioning

confidence: 99%

Feature extraction algorithms from MRI to evaluate quality parameters on meat products by using data mining

Caballero

2018

ELCVIA

Self Cite

View full text Add to dashboard Cite

This thesis proposes a new methodology to determine quality parameters of meat products (Iberian loin and ham) in a non-destructive way.Firstly, Magnetic Resonance Imaging (MRI) are obtained from meat products, evaluating three acquisition sequence (Spin Echo -SE-, Gradient Echo -GE-and Turbo 3D -T3D-). Later, MRI is analysed by applying different texture algorithms (GLCM, GLRLM and NGLDM) and fractals algorithms (CFA, FTA and OPFTA); the last two ones have been developed in this thesis. These algorithms extract texture features from the MRI. At the same time, the meat products are also analysed by means of physico-chemical and sensory techniques. Finally, different data mining techniques are applied on all obtained data: deductive (Multiple linear regression -MLR-), classification (Decision trees -DT-and Rules-based systems -RBS-) and prediction techniques (MLR and Isotonic regression -IR-).The accuracy of the analysis of quality parameters is affected by the MRI acquisition sequence, the algorithm used to analyse them and the data mining technique applied. In general, the use of SE as MRI acquisition sequence, and GLCM or OPFTA as image analysis algorithm could be indicated. Considering the data mining techniques, MLR and DT are appropriate, respectively, to deduce physico-chemical parameters and to classify as a function of salt content. Regarding to the predictive technique, MLR could be indicated. It offers reliable equations to determine the quality parameters, and, allows analysing the quality of meat products in a nondestructive, efficient, effective and accurate way.

show abstract

“…The proposed model allowed a satisfactory simulation of both the drying curve and the moisture profiles [77] . In the study of Perez-Palacios et al [78] , MRI and…”

Section: Mrimentioning

confidence: 96%

Recent Developments in Smart Drying Technology

Zhang

Mujumdar

2014

Drying Technology

View full text Add to dashboard Cite

With advances in computer, control and sensing technologies it is now possible to design smart dryers at least for certain products. In this paper, a generalized definition of smart (or intelligent) drying technology is proposed and discussed. Recent development in smart drying technology for fresh foods is reviewed briefly. Such technology can be cost effective in detecting and monitoring various food quality parameters which vary with time of the drying process, thus controlling the conditions of drying and producing high quality products. Some important categories of smart drying technology are listed and discussed; these include: biomimetic systems, computer vision technology, microwave dielectric spectroscopy, near infrared reflectance (NIR) spectroscopy, magnetic resonance imaging (MRI), ultrasonic techniques, electrostatic sensor technology and control systems for drying environment. Several latest applications of these smart drying technologies are analyzed. Key factors leading to success of smart drying technologies Downloaded by [Monash University Library] at 13:37 04 December 2014 2 are discussed. Developments, challenges, and applications, which represent a major step toward development of drying technology, are presented.

show abstract

Applying data mining and Computer Vision Techniques to MRI to estimate quality traits in Iberian hams

Cited by 54 publications

References 29 publications

Modeling salt diffusion in Iberian ham by applying MRI and data mining

Modeling salt diffusion in Iberian ham by applying MRI and data mining

Feature extraction algorithms from MRI to evaluate quality parameters on meat products by using data mining

Recent Developments in Smart Drying Technology

Contact Info

Product

Resources

About