Using a simple digital camera and SPA-LDA modeling to screen teas

Classification or screening analysis of natural unprocessed teas using simple digital images and a variable selection algorithm is described. The proposed methodology uses color histograms generated on free downloadable software ImageJ 1.44p as a source of analytical information. Two chemometric methods were compared for classification of the resulting images, namely Soft Independent Modeling of Class Analogy (SIMCA), and Linear Discriminant Analysis (LDA) with variable selection by the Successive Projections Algorithm (SPA). The results were evaluated in terms of errors found in a sample set separate from the modeling process. The choice of more informative photometric color attributes (red-green-blue (RGB), hue (H), saturation (S), brightness (B), and grayscale) for screening the tea samples was made during the color modeling because SIMCA failed to give good results. Therefore the data treatment used SPA-LDA, which correctly classified all samples according to their geographical regions, whether from Brazilian, Argentinian or foreign soils.

[1]  Bruce R. Kowalski,et al.  A comparison of five pattern recognition methods based on the classification results from six real data bases , 1979 .

[2]  Roberto Kawakami Harrop Galvão,et al.  UV–Vis spectrometric classification of coffees by SPA–LDA , 2010 .

[3]  S. Devahastin,et al.  Application of wavelet transform coupled with artificial neural network for predicting physicochemical properties of osmotically dehydrated pumpkin , 2009 .

[4]  A. de Juan,et al.  Multivariate image analysis: a review with applications , 2011 .

[5]  M. C. U. Araújo,et al.  Classification of edible vegetable oils using square wave voltammetry with multivariate data analysis. , 2009, Talanta.

[6]  Celio Pasquini,et al.  Assessment of infrared spectroscopy and multivariate techniques for monitoring the service condition of diesel-engine lubricating oils. , 2006, Talanta.

[7]  David A. Liñán,et al.  Chemometric interpretation of digital image colorimetry. Application for titanium determination in plastics , 2010 .

[8]  D. Massart,et al.  Standardization of near-infrared spectrometric instruments , 1996 .

[9]  Eun-hee Kim,et al.  Metabolic dependence of green tea on plucking positions revisited: a metabolomic study. , 2011, Journal of agricultural and food chemistry.

[10]  Roberto Kawakami Harrop Galvão,et al.  The successive projections algorithm for spectral variable selection in classification problems , 2005 .

[11]  Roberto Kawakami Harrop Galvão,et al.  Near infrared reflectance spectrometry classification of cigarettes using the successive projections algorithm for variable selection. , 2009, Talanta.

[12]  D. L. Massart,et al.  Decision criteria for soft independent modelling of class analogy applied to near infrared data , 1999 .

[13]  Mahdi Ghasemi-Varnamkhasti,et al.  Screening analysis of beer ageing using near infrared spectroscopy and the Successive Projections Algorithm for variable selection. , 2012, Talanta.

[14]  Paulo Henrique Gonçalves Dias Diniz,et al.  Indirect determination of sodium diclofenac, sodium dipyrone and calcium gluconate in injection drugs using digital image-based (webcam) flame emission spectrometric method , 2011 .

[15]  Pengcheng Nie,et al.  Using wavelet transform and multi-class least square support vector machine in multi-spectral imaging classification of Chinese famous tea , 2011, Expert Syst. Appl..

[16]  Manabendra Bhuyan,et al.  Non-destructive testing of tea fermentation using image processing , 2003 .

[17]  Wellington da Silva Lyra,et al.  A digital image-based flow-batch analyzer for determining Al(III) and Cr(VI) in water , 2013 .

[18]  Tormod Næs,et al.  Understanding the collinearity problem in regression and discriminant analysis , 2001 .

[19]  Maria Fernanda Pimentel,et al.  Screening analysis to detect adulteration in diesel/biodiesel blends using near infrared spectrometry and multivariate classification. , 2011, Talanta.

[20]  Andrew Fisher,et al.  The classification of tea according to region of origin using pattern recognition techniques and trace metal data , 2003 .

[21]  Mário César Ugulino Araújo,et al.  A digital image-based method for determining of total acidity in red wines using acid-base titration without indicator. , 2011, Talanta.

[22]  E. Farnworth,et al.  A review of latest research findings on the health promotion properties of tea. , 2001, The Journal of nutritional biochemistry.

[23]  Yi Lu,et al.  Fluoride content in tea and its relationship with tea quality. , 2004, Journal of agricultural and food chemistry.

[24]  Maria Fernanda Pimentel,et al.  Detection of adulteration in hydrated ethyl alcohol fuel using infrared spectroscopy and supervised pattern recognition methods. , 2012, Talanta.

[25]  Masaaki Tomizawa,et al.  New monitoring system for thermal power plants using digital image processing and sound analysis , 1995 .

[26]  M. Bancirova.  Comparison of the antioxidant capacity and the antimicrobial activity of black and green tea , 2010 .

[27]  Desire L. Massart,et al.  Supervised pattern recognition: the ideal method? , 1986 .

[28]  L. Teixeira,et al.  Screening analysis to detect adulterations in Brazilian gasoline samples using distillation curves , 2004 .

[29]  Paul Geladi,et al.  Principal Component Analysis , 1987, Comprehensive Chemometrics.

[30]  L. A. Stone,et al.  Computer Aided Design of Experiments , 1969 .

[31]  Quansheng Chen,et al.  Qualitative Identification of Tea by near Infrared Spectroscopy Based on Soft Independent Modelling of Class Analogy Pattern Recognition , 2005 .

[32]  Mário César Ugulino Araújo,et al.  Digital image-based titrations. , 2006, Analytica chimica acta.

[33]  Quansheng Chen,et al.  Feasibility study on identification of green, black and Oolong teas using near-infrared reflectance spectroscopy based on support vector machine (SVM). , 2007, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[34]  Arthur A. Teixeira,et al.  Thermophilic Anaerobic Digestion of Sugar Beet Tailings , 2008 .

[35]  Fernando López-García,et al.  Performance evaluation of soft color texture descriptors for surface grading using experimental design and logistic regression , 2008, Pattern Recognit..

[36]  E. Hines,et al.  Wavelet transform based image texture analysis for size estimation applied to the sorting of tea granules , 2007 .

[37]  Yong He,et al.  Application of image texture for the sorting of tea categories using multi-spectral imaging technique and support vector machine , 2008 .

[38]  Amod Kumar,et al.  Monitoring and grading of tea by computer vision – A review , 2011 .

[39]  D. Massart,et al.  The inclusion of double-channel ultraviolet spectrophotometry in an expert system for pharmaceutical analysis , 1986 .

[40]  Matti Pietikäinen,et al.  Rotation-invariant texture classification using feature distributions , 2000, Pattern Recognit..

[41]  L F Wang,et al.  Effects of heat processing and storage on flavanols and sensory qualities of green tea beverage. , 2000, Journal of agricultural and food chemistry.

[42]  R. Bandyopadhyay,et al.  Detection of optimum fermentation time for black tea manufacturing using electronic nose , 2007 .

[43]  Jiewen Zhao,et al.  Automated tea quality classification by hyperspectral imaging. , 2009, Applied optics.

[44]  Maria Fernanda Pimentel,et al.  Classification of blue pen ink using infrared spectroscopy and linear discriminant analysis , 2013 .

[45]  D. Coomans,et al.  Recent developments in discriminant analysis on high dimensional spectral data , 1996 .

[46]  G. Ferraro,et al.  Total polyphenol content and antioxidant capacity of commercially available tea (Camellia sinensis) in Argentina. , 2008, Journal of agricultural and food chemistry.

[47]  Mridul Hazarika,et al.  Chlorophylls and degradation products in orthodox and CTC black teas and their influence on shade of colour and sensory quality in relation to thearubigins , 1985 .

[48]  M. C. U. Araújo,et al.  The successive projections algorithm for variable selection in spectroscopic multicomponent analysis , 2001 .

[49]  Ralph Bernstein,et al.  Digital Image Processing of Earth Observation Sensor Data , 1976, IBM J. Res. Dev..

[50]  Celio Pasquini,et al.  Classification of Brazilian soils by using LIBS and variable selection in the wavelet domain. , 2009, Analytica chimica acta.

[51]  Hua Yu,et al.  A direct LDA algorithm for high-dimensional data - with application to face recognition , 2001, Pattern Recognit..

[52]  J. Blumberg,et al.  The Role of Tea in Human Health: An Update , 2002, Journal of the American College of Nutrition.

[53]  J. Zupan,et al.  Separation of data on the training and test set for modelling: a case study for modelling of five colour properties of a white pigment , 2003 .