Classification of Defects in Potato Using Grey Level Co-Occurrence Matrix and Support Vector Machine

Dhulipalla Ravindra Babu; R. C. Verma; Navneet Kumar Agrawal; Isha Suwalk

doi:10.52151/jae2023602.1805

Authors

Dhulipalla Ravindra Babu Ph.D. Scholar,Department of Processing and Food Engineering,College of Technology and Engineering, Maharana Pratap University of Agriculture and Technology, Udaipur, Rajasthan, India. Author
R. C. Verma Professor,Department of Processing and Food Engineering,College of Technology and Engineering, Maharana Pratap University of Agriculture and Technology, Udaipur, Rajasthan, India. Author
Navneet Kumar Agrawal Assistant Professor, Department of Electronics and Communication Engineering, College of Technology and Engineering, Maharana Pratap University of Agriculture and Technology, Udaipur, Rajasthan, India. Author
Isha Suwalk ex-Ph.D. Scholar. Department of Electronics and Communication Engineering, College of Technology and Engineering, Maharana Pratap University of Agriculture and Technology, Udaipur, Rajasthan, India. Author

DOI:

https://doi.org/10.52151/jae2023602.1805

Keywords:

Grey level co-occurrence matrix, potato classification, support vector machine

Abstract

An attempt was made to classify potato into five classes based on features of grey level co-occurrence matrix properties and support vector machine. Potato images were captured using the developed experimental set-up, which had a resolution of 0.22 mm per pixel. The four parameters of grey level co-occurrence matrix viz. variance, correlation, uniformity, and homogeneity were calculated from each image, and the data set was prepared. Sample sizes of crack, rotten, sprout, good, and skin-peel potatoes were 75, 39, 153, 96, and 635, respectively. Cracked, rotten, sprouted, good, and skin-peeled potato images were labelled as 1, 2, 3, 4, and 5, respectively. With addition of labels, the data set size increased to 998-by-five. Feature data set of 998-by-5 was fed into classification learner app in MATLAB. Combined parameters of grey level co-occurrence matrix of variance (contrast), correlation, uniformity (energy), and homogeneity were used in potato classifications. A cubic support vector machine had classification accuracy of 99.5 per cent. Quality parameters like true positive and positive predictive values were studied for cubic support vector machine model. True positive rates of 100, 97, 98, 99, and 100 were observed for crack, rotten, sprouted, good, and skin-peel categories, respectively. Crack and skin-peel categories had same number of potatoes in manual and cubic support vector machine classification. Mis-classified potatoes in cubic support vector machines were less as compared to manual classification by one, two, and two potatoes in rotten, sprouted, and good categories, respectively.

References

Alhindi T J; Kalra S; Ng Ka Hin; Afrin A; Tizhoosh H R. 2018. Comparing lbp, hog and deep features for classification of histopathology images. In: IEEE Proc. International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil, 1-7. doi: 10.1109/IJCNN.2018.8489329

Amrinder S B; Kawaljeet S. 2016. Potato defect detection using fuzzy c-mean clustering-based segmentation. Indian J. Sci. Technol., 9(32), 1-6.

Anon. 2017. India: Monthly Report Potato. PotatoPRO./ Food Innovation Online Corp. https://www.potatopro.com/india/potato-statistics. Accessed in August 2022

Anon. 2019. Sensitivity and Specificity. http://en.wikipedia.org/wiki/Sensitivity_and_specificity.Wikipedia. Accessed in August 2022

Anon. 2022. Production Volume of Potatoes in India. www.statistica.com. Statista. India. Accessed in August 2022

Aquino A; Diago M P; Millan B; Javier T. 2017. A new methodology for estimating the grape vine berry number per cluster using image analysis. Biosyst. Eng.,156, 80-95.

Bade A; Dale M P; Jemshid K. 2016. Quality assessment of biscuits using computer vision. ICACT J. Image Video Process., 7, 1285-1289.

Caprara C; Martelli R. 2015. Image analysis implementation for evaluation of external potato damage. Appl. Math. Sci., 9, 4029-4041.

Eissa A H A; Khalik A. 2012. Understanding Color Image Processing by Machine Vision for Biological Materialsn. In: Structure and Function of Food Engineering, Chapter 10, 227-274.

Hassankhani R; Navid H; Seyedarabi H. 2012. Potato surface defect detection in machine vision. Afr. J. Agric. Res., 7, 844-850. doi: 10.5897/AJAR11.2049

Hassankhani R; Navid H. 2012. Potato sorting based on size and color in machine vision system. J. Agric. Sci.,4, 235-244.

Jin J; Li J; Liao G; Yu X; Leo C V. 2009. Methodology for potatoes defects detection with computer vision. In: Proc. Int. Sym. Inf. Process., China, August 21-23, 346-351.

Kiani S; Minaei S. 2016. Potential application of machine vision technology to saffron (Crocus Sarivus L.) quality characterization. Food Chem., 212, 392-394.

MATLAB. 2018. Help Documentation. The Mathworks, Inc. Uinted States of America, Ver. 9.5.0.944444.

Milan S; Vaclav H; Roger B. 2015. Image Processing, Analysis, and Machine Vision. Cengage Learning, 200 First Stamford Place, 4th Floor, Stamford, CT 06902, USA, fourth edition, pp: 870. ISBN-13: 978-1-133- 59360-7

Mehrdad F; Parviz A M; Saeed A N. 2012. Tomato classification and sorting with machine vision using SVM, MLP and LVQ. Int. J. Agric. Crop Sci., 4, 1083-1088.

Mehrdad B; Ahmad B; Saeed M; Jalal K; Nasser B K. 2015. Machine vision system for grading of dried figs. Comput. Electron. Agric., 119, 158-165.

Mohammad E B; Masoud H; Ansari K. 2017. Feasibility of using image processing and colorimetric measurements to estimate the physicochemical properties of raw cane sugars. Sugar Technol.,19, 305-316.

Mora M; Avila F; Moras C B; Gonzalo M; Jeissey O C; Sigfredo F. 2016. Automated computation of leaf area index from fruit trees using improved image processing applied to canopy cover digital photograpies. Comput. Electron. Agric., 123, 195-202.

Nashat S; Abdulla A; Abdulla M Z. 2014. Machine vision for crack inspection of biscuits featuring pyramid detection scheme. J. Food Eng., 120, 233-247.

Nasser B K; Teymour T; Hassan G; Mohammad H K; Ahmad B. 2013. Applied machine vision and artificial neural network for modelling and controlling of the grape drying process. Comput. Electron. Agric., 98, 205-213.

Prabha D S; Kumar J S. 2015. Assessment of banana fruit maturity by image processing technique. J. Food Sci. Technol., 51, 1316-1327.

Rani S; Prasoon M. 2013. Analysis of potato production performance and yield variability in India. Potato J., 40, 38-44.

Razmooy N; Mousavi B S; Soleymani F. 2012. A real time mathematical computer method for potato inspection using machine vision. Comput. Math. Appl., 63, 268-279.

Rivera NV; Sanchis J G; Perej J C; Carrasco J; Giraldo M; Lorento D; Cubero S; Blasco J. 2014. Early detection of mechanical damage in mango using near infra-red hyper spectra images and machine learning. Biosyst. Eng., 122, 91-98.

Saad F S A; Ibrahim M F; Shakaff A Y M; Zakaria A; Abdulla M Z. 2015. Shape and grading of mangoes using visual imaging. Comput. Electron. Agric., 115, 51-56.

Sahana M; Anita H B. 2017. Automatic classification of south Indian regional fruits using image processing. Indian J. Sci. Technol., 10, 1-4.

Samanta Debabrata; Chaudhury P; Ghosh A. 2012. Scab diseases detection of potato using image processing. Int. J. Comput. Trends Technol., 3, 109-113.

Spreer W; Muller J. 2011. Estimating the mass of mango fruit from its geometric dimensions by optical measurement. Comput. Electron. Agric., 75, 125-131.

Zhang H; Sha Z. 2013. Product classification based on SVM and PHOG descriptor. Int. J. Comput. Sci. Network Secuirity, 13, 1-4.