Comparative study of transform-based image texture analysis for the evaluation of banana quality using an optical backscattering system

Abstract In this study, the application of a backscattering imaging system with different approaches of transform-based image texture analysis for the evaluation of banana quality at different ripening stages was investigated with Wavelet, Gabor and Tamura transforms. The attenuated images of the fruits were acquired using Laser Light Backscattering Imaging (LLBI) with laser diodes emitting light at three wavelengths viz 532, 660, and 830 nm. The elasticity, chlorophyll index and soluble solids content (SSC) of each sample were measured as reference parameters by using a texture analyser, a Delta Absorbance (DA) meter, and a refractometer, respectively. The performance of the extracted features from the selected transform-based image texture analysis for analysing the quality parameters of the fruit was evaluated by means of an artificial neural network (ANN) and a support vector machine (SVM). The results indicated that there were significant changes of elasticity, chlorophyll index and SSC as the ripening stages increased. Prediction model analysis showed that the Wavelet transform exhibited the most reliable results for all of the reference parameters followed by Tamura and the Gabor transform. The results also revealed that analysis using an ANN approach recorded better performance than SVM as reflected by higher coefficient of determination (R 2 ) values. Thus, this study indicated that an LLBI system with transform-based image texture analysis coupled with computational intelligence techniques can be used for the evaluation of the quality of bananas.

[1]  Mahmoud Omid,et al.  Analysis of texture-based features for predicting mechanical properties of horticultural products by laser light backscattering imaging , 2013 .

[2]  R. Lu.  Multispectral imaging for predicting firmness and soluble solids content of apple fruit , 2004 .

[3]  Aiguo Ouyang,et al.  Nondestructive measurement of soluble solid content of navel orange fruit by visible-NIR spectrometric technique with PLSR and PCA-BPNN. , 2010 .

[4]  Rajiv Kumar,et al.  Changes in sugars, organic acids, amino acids, lipid constituents and aroma characteristics of ripening mango (Mangifera indica L) fruit , 1989 .

[5]  R. Blomhoff,et al.  Colour of post‐harvest ripened and vine ripened tomatoes (Lycopersicon esculentum Mill.) as related to total antioxidant capacity and chemical composition , 2004 .

[6]  Marcus Nagle,et al.  Laser light backscattering to monitor moisture content, soluble solid content and hardness of apple tissue during drying , 2011 .

[7]  Marsyita Hanafi,et al.  Application and potential of backscattering imaging techniques in agricultural and food processing – A review , 2016 .

[8]  José Blasco,et al.  Early decay detection in citrus fruit using laser-light backscattering imaging , 2013 .

[9]  D. Gabor,et al.  Theory of communication. Part 1: The analysis of information , 1946 .

[10]  Manuela Zude,et al.  Analysis of laser light propagation in kiwifruit using backscattering imaging and Monte Carlo simulation , 2009 .

[11]  E Hoehn,et al.  Efficacy of instrumental measurements for determination of minimum requirements of firmness, soluble solids, and acidity of several apple varieties in comparison to consumer expectations , 2003 .

[12]  A. Torricelli,et al.  Non-destructive analysis of anthocyanins in cherries by means of Lambert–Beer and multivariate regression based on spectroscopy and scatter correction using time-resolved analysis , 2011 .

[13]  Gunnar Rätsch,et al.  Engineering Support Vector Machine Kerneis That Recognize Translation Initialion Sites , 2000, German Conference on Bioinformatics.

[14]  Changhong Liu,et al.  Application of Multispectral Imaging to Determine Quality Attributes and Ripeness Stage in Strawberry Fruit , 2014, PloS one.

[15]  A. Peirs,et al.  Nondestructive measurement of fruit and vegetable quality by means of NIR spectroscopy: A review , 2007 .

[16]  Marsyita Hanafi,et al.  Prediction of quality attributes and ripeness classification of bananas using optical properties , 2016 .

[17]  Muin J. Khoury,et al.  Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes , 2010, BMC Medical Informatics Decis. Mak..

[18]  R. Lu,et al.  Measurement of the optical properties of fruits and vegetables using spatially resolved hyperspectral diffuse reflectance imaging technique , 2008 .

[19]  M. Ebrahimi,et al.  Neural network and SVM classifiers accurately predict lipid binding proteins, irrespective of sequence homology. , 2014, Journal of theoretical biology.

[20]  M. D. Cox,et al.  Discrete wavelet analysis of power system transients , 1996 .

[21]  Ron B. H. Wills,et al.  Postharvest: an introduction to the physiology & handling of fruit, vegetables & ornamentals. , 1998 .

[22]  Luis Romeral,et al.  Fault Detection in Induction Machines Using Power Spectral Density in Wavelet Decomposition , 2008, IEEE Transactions on Industrial Electronics.

[23]  Klaus Gottschalk,et al.  An Approach for Monitoring the Moisture Content Changes of Drying Banana Slices with Laser Light Backscattering Imaging , 2008 .

[24]  Kontogeorgos Achilleas,et al.  Marketing aspects of quality assurance systems , 2008 .

[25]  Frederic Truchetet,et al.  Wavelet transform to discriminate between crop and weed in perspective agronomic images , 2009 .

[26]  D. Cozzolino,et al.  Prediction of Colour and pH in Grapes Using a Diode Array Spectrophotometer (400–1100 nm) , 2004 .

[27]  E. Vandamme,et al.  Pectin, pectinase and protopectinase: production, properties, and applications. , 1993, Advances in applied microbiology.

[28]  I. Daubechies.  Orthonormal bases of compactly supported wavelets , 1988 .

[29]  Manuela Zude,et al.  Non-destructive analyses of apple quality parameters by means of laser-induced light backscattering imaging , 2008 .

[30]  Da-Wen Sun,et al.  Recent applications of image texture for evaluation of food qualities—a review , 2006 .

[31]  Chuanqi Zhang,et al.  Artificial neural network modeling of dissolved oxygen in the Heihe River, Northwestern China , 2013, Environmental Monitoring and Assessment.

[32]  Kathirvalavakumar Thangairulappan,et al.  Face Representation Using Combined Method of Gabor Filters, Wavelet Transformation and DCV and Recognition Using RBF , 2012 .

[33]  J. Roger,et al.  Non-destructive tests on the prediction of apple fruit flesh firmness and soluble solids content on tree and in shelf life , 2006 .

[34]  Iman Attarzadeh,et al.  A novel soft computing model to increase the accuracy of software development cost estimation , 2010, 2010 The 2nd International Conference on Computer and Automation Engineering (ICCAE).

[35]  R. Paull,et al.  Postharvest Variation in Cell Wall-Degrading Enzymes of Papaya (Carica papaya L.) during Fruit Ripening. , 1983, Plant physiology.

[36]  Enrico Bignetti,et al.  Exploring New Frontiers in Total Food Quality Definition and Assessment: From Chemical to Neurochemical Properties , 2008 .

[37]  Marsyita Hanafi,et al.  Using absorption and reduced scattering coefficients for non-destructive analyses of fruit flesh firmness and soluble solids content in pear (Pyrus communis ‘Conference’)—An update when using diffusion theory , 2017 .

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

[39]  Yankun Peng,et al.  Prediction of apple fruit firmness and soluble solids content using characteristics of multispectral scattering images , 2007 .

[40]  Siti Khairunniza Bejo,et al.  Quality evaluation of watermelon using laser-induced backscattering imaging during storage , 2017 .

[41]  D Haussler,et al.  Knowledge-based analysis of microarray gene expression data by using support vector machines. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[42]  V. Mcglone,et al.  Kiwifruit Firmness by near Infrared Light Scattering , 1997 .

[43]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[44]  William R. Raun,et al.  Spectral Reflectance to Estimate Genetic Variation for In-Season Biomass, Leaf Chlorophyll, and Canopy Temperature in Wheat , 2006 .

[45]  Manuela Zude,et al.  An approach for monitoring the chilling injury appearance in bananas by means of backscattering imaging , 2013 .

[46]  José Miguel Aguilera,et al.  Image analysis of changes in surface color of chocolate , 2005 .

[47]  M. Schreiner,et al.  Current understanding and use of quality characteristics of horticulture products , 2013 .

[48]  Ron B. H. Wills,et al.  Postharvest: An Introduction to the Physiology and Handling of Fruit and Vegetables , 2016 .

[49]  Tony K. McGhie,et al.  Skin colour and pigment changes during ripening of 'Hass' avocado fruit , 2004 .

[50]  Da-Wen Sun,et al.  Advances in Feature Selection Methods for Hyperspectral Image Processing in Food Industry Applications: A Review , 2015, Critical reviews in food science and nutrition.

[51]  A. D. Whittaker,et al.  WAVELET TEXTURAL FEATURES FROM ULTRASONIC ELASTOGRAMS FOR MEAT QUALITY , 1997 .

[52]  Manuela Zude,et al.  Kinetic Model for Colour Changes in Bananas During the Appearance of Chilling Injury Symptoms , 2012, Food and Bioprocess Technology.

[53]  Hideyuki Tamura,et al.  Textural Features Corresponding to Visual Perception , 1978, IEEE Transactions on Systems, Man, and Cybernetics.

[54]  Varun Jaiswal,et al.  DRPPP: A machine learning based tool for prediction of disease resistance proteins in plants , 2016, Comput. Biol. Medicine.