Screening for Coffee Adulteration Using Digital Images and SPA-LDA

详细信息    查看全文

• 作者：Urijatan Teixeira de Carvalho Polari Souto…
• 关键词：Coffee ; Adulteration ; Digital images ; Color histograms ; Successive projections algorithm
• 刊名：Food Analytical Methods
• 出版年：2015
• 出版时间：July 2015
• 年：2015
• 卷：8
• 期：6
• 页码：1515-1521
• 全文大小：693 KB
• 参考文献：Almeida VE, Costa GB, Fernandes DDS, Diniz PHGD, Brand?o D, Medeiros ACD, Véras G (2014) Using color histograms and SPA-LDA to classify bacteria. Anal Bioanal Chem 406:5989-995. doi:10.-007/?s00216-014-8015-1 View Article
  Associa??o Brasileira da Indústria de Café (2014) Programa de Qualidade do Café. http://?www.?abic.?com.?br/?publique/?cgi/?cgilua.?exe/?sys/?start.?htm??sid=-5 . Accessed 24 July 2014
  Baggenstoss J, Poisson L, Kaegi R, Perren R, Escher F (2008) Coffee roasting and aroma formation: application of different time-temperature conditions. J Agric Food Chem 56:5836-846. doi:10.-021/?jf800327j View Article
  Ballabio D, Consonni V (2013) Classification tools in chemistry. Part 1: linear models. PLS-DA. Anal Methods 5:3790-798. doi:10.-039/?C3AY40582F View Article
  Bekedam EK, Loots MJ, Schols HA, Van Boekel MAJS, Smit G (2008) Roasting effects on formation mechanisms of coffee brew melanoidins. J Agric Food Chem 56:7138-145. doi:10.-021/?jf800999a View Article
  Bicho NC, Leit?o AE, Ramalho JC, Lidon FC (2012) Use of colour parameters for roasted coffee assessment. Cienc Tecnol Aliment 32:436-42. doi:10.-590/?S0101-2061201200500006- View Article
  Bicho NC, Lidon FC, Ramalho JC, Leit?o AE (2013) Quality assessment of Arabica and Robusta green and roasted coffees—a review. Emir J Food Agric 25:945-50. doi:10.-755/?ejfa.?v25i12.-7290 View Article
  Diniz PHGD, Dantas HV, Melo KDT, Barbosa MF, Harding DP, Nascimento ECL, Pistonesi MF, Band BSF, Araújo MCU (2012) Using a simple digital camera and SPA-LDA modeling to screen teas. Anal Methods 4:2648-652. doi:10.-039/?c2ay25481f View Article
  Diniz PHGD, Gomes AA, Pistonesi MF, Band BSF, Araújo MCU (2014) Simultaneous classification of teas according their varieties and geographical origins by using NIR spectroscopy and SPA-LDA. Food Anal Methods. doi:10.-007/?s12161-014-9809-7
  Domingues DS, Pauli ED, Abreu JEM, Massura FW, Cristiano V, Santos MJ, Nixdorf SL (2014) Detection of roasted and ground coffee adulteration by HPLC by amperometric and by post-column derivatization UV–Vis detection. Food Chem 146:353-62. doi:10.-016/?j.?foodchem.-013.-9.-66 View Article
  Domínguez MA, Diniz PHGD, Di Nezio MS, Araújo MCU, Centurión ME (2014) Geographical origin classification of Argentinean honeys using a digital image-based flow-batch system. Microchem J 112:104-08. doi:10.-016/?j.?microc.-013.-9.-08 View Article
  Ebrahimi-Najafabadi H, Leardi R, Oliveri P, Casolino MC, Jalali-Heravi M, Lanteri S (2012) Detection of addition of barley to coffee using near infrared spectroscopy and chemometric techniques. Talanta 99:175-79. doi:10.-016/?j.?talanta.-012.-5.-36 View Article
  Gonzalez RC, Woods RE (1992) Digital image processing, 3rd edn. Addison-Wesley, Boston
  International Coffee Organization (2014) Exporting countries: total production. http://?www.?ico.?org/?prices/?po.?htm . Accessed 4 June 2014
  Kennard RW, Stone LA (1969) Computer aided design of experiments. Technometrics 11:137-48. doi:10.-080/-0401706.-969.-0490666 View Article
  Lavine, B. K. (2009) In Comprehensive chemometrics, vol. 3; Walczak, B.; Tauler, R.; Brown, S., eds.; Elsevier, Oxford
  Massart DL, Vandeginste BGM, Buydens SJ, Lewi PJ, Smeyers-Verbeke J (1998) Handbook of chemometrics and qualimetrics, part A. Elsevier, Amsterdam
  Meilgaard MC, Carr BT, Civille GV (2006) Sensory evaluation techniques, 4th edn. CRC, Boca Raton
  Mendon?a JCF, Franca AS, Oliveira LS (2008) Physical characterization of non-defective and defective Arabica and Robusta coffees before and after roasting. J Food Eng 92:474-79. doi:10.-016/?j.?jfoodeng.-008.-2.-23 View Article
  Ministério da Agricultura, Pecuária e Abastecimento (2010) Regulamento técnico para o café torrado em gr?o e para o café torrado e moído. Instru??o Normativa No. 16, de 24 de Maio de 2010
  Nicoli MC, Anese M, Manzocco L, Lerici CR (1997) Antioxidant properties of coffee brews in relation to the roasting degree. LWT-Food Sci Technol 30:292-97. doi:10.-006/?fstl.-996.-181 View Article
  Pauli ED, Barbieri F, Garcia PS et al (2014) Detection of ground roasted coffee adulteration with roasted soybean and wheat. Food Res Int. doi:10.-016/?j.?foodres.-014.-2.-32
  Reis N, Franca AS, Oliveira LS (2013) Performance of diffuse reflectance infrared Fourier transform spectroscopy and chemometrics for detection of multiple adulterants in roasted and ground coffee. LWT-Food Sci Technol 53:395-01. doi:10.-016/?j.?lwt.-013.-4.-08 View Article
  Sano EE, Assad ED, Cunha SAR, Correa TBS, Rodrigues HR (2003) Quantifying adulteration in roast coffee powders by digital image processing. J Food Qual 26:123-34. doi:10.-111/?j.-745-4557.-003.?tb00232.?x View Article
  Soares SFC, Gomes AA, Galv?o Filho AR, Araújo MCU, Galv?o RKH (2013) The successive projections algorithm. Trends Anal Chem 42:84-8. doi:10.-016/?j.?trac.-012.-9.-06 View Article
• 作者单位：Urijatan Teixeira de Carvalho Polari Souto (1)
  Mayara Ferreira Barbosa (1)
  Hebertty Vieira Dantas (1)
  Aline Santos de Pontes (1)
  Wellington da Silva Lyra (1)
  Paulo Henrique Gon?alves Dias Diniz (2)
  Mário César Ugulino de Araújo (1)
  Edvan Cirino da Silva (1)
  
  1. Departamento de Química, Universidade Federal da Paraíba, P.O. Box 5093, 58051-970, Jo?o Pessoa, PB, Brazil
  2. Centro de Ciência e Tecnologia, Departamento de Química, Universidade Estadual da Paraíba, Campina Grande, PB, Brazil
  
• 刊物类别：Chemistry and Materials Science
• 刊物主题：Chemistry
  Food Science
  Chemistry
  Microbiology
  Analytical Chemistry
  
• 出版者：Springer New York
• ISSN：1936-976X

文摘

In this paper, we propose a new methodology to identify adulterations in ground roasted coffees (due to the presence of husks and sticks) using digital images and the successive projections algorithm for variable selection in association with linear discriminant analysis (SPA-LDA). A simple document scanner was used for capturing the images, and a Petri dish support with eight circular holes (one for each sample) to be scanned was employed. Color histograms in the hue-luminosity-saturation (HLS) channels extracted from the digital images were used as input data and statistically evaluated using supervised pattern recognition techniques. For comparison with SPA-LDA, soft independent modeling by class analogy (SIMCA) and partial least squares discriminant analysis (PLS-DA) were also used. In general, SPA-LDA provided significantly better performance than the other classification models, reaching a mean accuracy of 92.5?% for both the training and test sets, while SIMCA and PLS-DA attained only 71.5 and 85.5?%, respectively. More specifically, all of the models presented high rates (above 90?%) for sensitivity and specificity (in the test set samples classification), except SIMCA, which presented a specificity rate of 76?%. Moreover, the SPA-LDA model generally showed the lowest classification error rates. As such, it is a more adequate chemometric tool for discriminating pure coffee samples and adulterated by husks and sticks. The proposed strategy avoided laborious sample preparation, and additional operational costs, assessing coffee adulteration by husks and sticks.