Adaptive threshold back propagation neural network for rice grain classification using variance and co-variance colour features


Ksh. Robert Singh,Saurabh Chaudhury,



Image,Colour,Features,Variance,Co-variance,Neural Network,


This paper presents a simple and fast feature extraction technique for classification of four varieties of rice grain. Three colour models (RGB, HSV and HSI) are obtained from the input colour images. Variance and Covariance features are then extracted from each of the three colour models. The classification of rice grains are then carried out using a Back Propagation Neural Network with adaptive thresholding. The computational time for feature extraction and their classification accuracies are also compared with other feature extraction techniques. It is found that the time taken using variance and covariance features extraction technique is relatively less compared to other feature extraction techniques. It is also seen that the proposed feature extraction technique is able to achieve better classification accuracy as compared to other feature extraction techniques discussed in this paper. Results suggest that the proposed technique is able to yield higher classification accuracy than that of other statistical classifiers like K- Nearest Neighbour (K-NN), Naïve Bayes and Support Vector Machine (SVM). The performances of all four classifiers were also tested against standard data sets.


I. A. Douik, and M. Abdellaoui, “Cereal grain classification by optimum
features and intelligent classifiers,” Int. J. of computer, communications and
control, Vol.: 5, pp. 506-516, 2010 6 1
II. Agung Wibowo, Yuri Rahayu, Andi Riyanto and Taufik Hidayatulloh,
“Classification algorithm for edible mushroom identification,” International
conference on Information and communications Technology (ICOIACT),
Indonesia, pp. 250-253, 2018 38 2
III. Alireza Pazokia, and Zohreh Pazokia, “Classification system for rain fed
wheat grain cultivars using artificial neural network,” African J.
Biotechnology, Vol.: 10, Issue: 41, pp. 8031-8038, 2011 16 3
IV. Alireza Pourreza, Hamidreza Pourreza, and M.H. Hbbaspour-Fard,
“Identification of nine Iranian wheat seed varieties by textural analysis with
image processing,” Computers and Electronics in Agriculture. Vol.: 83, pp.
102-108, 2012 19 4
V. Alireza Sanaeifar, Adel Bakhshipour, and Miguel Dela Guardia, “Prediction
of banana quality indices from colour features using support vector
regression,” Talanta. Vol.: 148, pp. 54-61, 2016 29 5
VI. A.R. Pazoki, F. Farokhi, and Z. Pazoki, “Classification of rice grain varieties
using two artificial neural networks (MLP and Neuro-Fuzzy),” The Journal of
Animal & Plant Sciences. Vol.: 24, Issue: 1, pp. 336-343, 2014 15 6
VII. Aydin Gullu, Ozan AKI, and Erdem Ucar, “Classification of rice grain using
image processing and machine learning techniques,” International Scientific
Conference, pp. 352-354, 2015 22 7
VIII. B.S. Anami, D.G. Savakar, and Aziz Makandar, “A neural network model for
classification of Bulk grain samples based on colour and texture,” Proceeding
of International conference on cognition and recognition, pp. 359-368, 2005
17 8
IX. D.K. Srivastava, and Lekha Bhambhu, “Data Classification Using Support
Vector Machine,” Journal of Theoretical and Applied Information
Technology, Vol.: 12, Issue: 1, pp. 1-7, 2010 23 9
X. F. Guevara-Hernandez, and J. Gonez-Gil, “A machine vision system for
classification of wheat and barley grain kernels,” Spanish Journal of
Agricultural Research. Vol.: 9, Issue: 3, pp. 672-680, 2011 24 10

XI. Federico Marini, Remo Bucci, and Antonio L. Magri, “Classification of 6
durum wheat cultivars from Sicily (Italy) using artificial neural network,”
Chemometrics and intelligent laboratory systems, Vol.: 90, pp.1-7, 2007 7 11
XII. Harpret Kaur, and Baljit Singh, “Classification and grading of rice using
multi-class SVM,” International Journal of scientific and research
publication, Vol.: 3, Issue: 4, pp. 1-5, 2013 25 12
XIII. H.K. Mebatsion, J.Paliwal, and D.S. Jayas, “Automatic classification of nontouching
cereal grain in digital image using limited morphological and colour
features,” Computers and electronics in Agriculture. Vol.: 90, pp. 99-105,
2013 3 13
XIV. Ian C. Navotas, Charisse Nadine V. Santos, Earl John M. Balderrama,
Francia Emmanuelle B. Candido, Aloysius John E. Villacanas, and Jessica S.
Velasco, “Fish identification and freshness classification through image
processing using artificial neural network,” ARPN Journal of Engineering
and Applied Sciences, Vol.:13, Issue: 18,pp. 4912-4922, 2018 46 14
XV. Iman Golpour, Jafar Amir Parian, and Reza Amir Chayjan, “Identification
and classification of bulk paddy,brown,and white rice cultivars with colour
features extraction using image analysis and neural network. Czech J. Food
Sci. Vol.: 32, Issue: 3, pp. 280-287, 2014 26 15
XVI. Irena Orina, Marena Manley, and Paul J williams, “Non-destructive
technique for detection of fungal infection in cereal grain”, Food Research
International. Vol.: 100, pp. 74-86, 2017 32 16
XVII. Irmgard Hein, Aifonso Rojas-Dominguez, Manuel Ornelas, Giulia D’Ercole,
and Lisa Peloschek, “Automatic classification of archaeological ceramic
materials by means of texture measures,” Journal of Archaeological Science
Report, Vol.: 21, pp. 921-928, 2018 44 17
XVIII. Ji Sang Bae, Sang-Ho Lee, Kang Sun Choi, and Jonk ok kim, “Robust skin
roughness estimation based on co-occurrence matrix,” J. Vis. Commun.
Image R., Vol.: 46, pp. 13-22, 2017 33 18
XIX. J. Paliwal, N.S. Visen, and D.S. Jayas, “Evaluation of neural network
architecture for cereal grain classification using morphological features.” J.
argic. Engg Res., Vol.: 79, Issue: 4, pp. 361-370, 2001 4 19
XX. J. Paliwal, N.S. Visen, and D.S. Jayas, “Cereal grain and dockage
identification using machine Vision,” Bio-system Engineering. Vol.: 85,
Issue: 1, pp. 51-57, 2003 14 20
XXI. Kamil Dimililer and Ehsan Kiani, “Application of Back Propagation Neural
Networks on Maize plant detection”. Procedia Computer Science, 9th
International Conference on theory and applications of soft computing,
computing with words and perceptron, ICSCCW, Hungary, pp. 376-381,
2017 34 21
XXII. Kivanc Kilic, Ismail Hakki Boyaci, and Hamit KoKsel, “A classification
system for beans using computer vision system and artificial neural
networks,” Journal of Food Engineering, Vol.: 78, pp. 897-904, 2007 8 22

XXIII. K. Neelamma Patil, S. Virendra, and Malemath, “Colour and texture based
identification and classification of food grains using different colour models
and Haralick features,” International journal of Computer Science and
Engineering. Vol.: 3, pp. 3669-3679, 2011 21 23
XXIV. Kusworo Adi, Catur Edi Widodo, Aris Puji Widodo, Rahmat Gernowo, Adi
Pamungkas, and Rizky Ayomi Syifa, “Detection lungs cancer using Gray
level co-occurrence matrix (GLCM) and Back propagation neural network
classification,” Journal of Engineering Science and Technology Review,
Vol.:11, Issue: 2, pp. 8-12, 2018 45 24
XXV. Lin Mar Oo and Nay Zar Aung, “A simple and efficient method for automatic
strawberry shape and size estimation and classification,” Biosystem
Engineering, Vol.: 170, pp. 96-107, 2018 39 25
XXVI. LIU Zhao-yan, CHENG Fang, and YING Yi-bin, “Identification of rice seed
varieties using neural network,” Journal of Zhejiang University SCIENCE.
Vol.: 6B, Issue: 11, pp.1095-1100, 2005 9 26
XXVII. Malay Kishore Dutta, Ashish Issac, Navroj Minhas, and Biplab Sarker,
“Image processing based method to assess fish quality and freshness,”
Journal of Food Engineering. Vol.: 177, pp. 50-58, 2016 30 27
XXVIII. Malgorzata Charytanowicz, PiotrKulezycki and piotr A. Kowalski, “An
evaluation of utilized geometric features for wheat grain classification using
X-ray image,” Computers and Electronics in agriculture. Vol.: 144, pp. 260-
268, 2018 40 28
XXIX. Muhammad Tahir, “Pattern analysis of protein image from fluorescence
microscopy using GLCM,” Journal of King Saud University Science, Vol.:
30, pp. 29-40, 2018 41 29
XXX. N.S. Visen, J. Paliwal, D.S. Jayas, “Image analysis of bulk grain samples
using neural network,” Canadian Biosystem Engineering. Vol.: 46, pp. 7.11-
7.15, 2004 18 30
XXXI. P. Vithu, and J.A. Moses, “Machine vision system for food grain quality
evaluation: A review,” Trends in food Science and Technology. Vol.: 56, pp.
13-20, 2016 31 31
XXXII. Rafael C Gonzalez and Richard E Woods, “Digital Image Processing,” New
Delhi, Pearson Prentice Hall (2009). 2 32
XXXIII. R. Choudhary, J. Paliwal, and D.S. Jayas, “Classification of cereal grain
using wavelet, morphological, colour and texture features of non-touching
kernel,” Biosystem Engineering, Vol.: 99, pp. 330-337, 2008 5 33
XXXIV. Sabiq Adzhani Hammam, Tito Waluyo Purboyo, and Randy Erfa Saputra,
“Cotton texture segmentation based on image texture analysis using gray
level run length and Ecludian distance,” Journal of theoretical and applied
information technology. Vol.: 95, Issue: 24, pp. 6915-6923, 2017 35 34
XXXV. Saurabh Agrawal, N.K. Verma, & Prateek Tamrakar, “Content based colour
image classification using SVM,” Eight International conferences on
information technology: New generation (2011), pp. 1090-1094, 2011 27 35
XXXVI. Silvia Grassi, Ernestina Casiraghi, and Cristina Alamprese, “Fish fillet
authentication by image analysis,” Journal of food Engineering, Vol.: 234,
pp. 16-23, 2018 43 36

XXXVII. Sitt Wetenriajeng, Ansar Suyuti, Intan Sari arena and Ingrid Nurtanio,
“Classification of Passion fruit’s ripeness using K-mean clustering and
Artificial neural network,” International conference on Information and
communications Technology (ICOIACT), Indonesia, pp. 304-309, 2018 42
XXXVIII. S. Jayaraman, S. Esakkirajan, and T. Veerakumar, “Digital Image
Processing,” New Delhi, Tata McGraw Hill Education (2009). 1 38
XXXIX. S. Majundar, and D.S. Jayas, “Classification of bulk samples of cereal grain
using machine vision,” J. Agric. Engng Res. Vol.: 73, pp. 35-47, 1999 20 39
XL. S. Majundar, and D.S. Jayas, “Classification of cereal grain using machine
vision. I. Morphology model,” Transaction of the ASAE, Vol.: 43, Issue: 6,
pp.1669-1675, 2000 10 40
XLI. S. Majundar, and D.S Jayas, “Classification of cereal grain using machine
vision. II. Colour model,” Transaction of the ASAE. Vol.: 43, Issue: 6,
pp.1677-1680, 2000 11 41
XLII. S. Majundar, and D.S. Jayas, “Classification of cereal grain using machine
vision.III. Texture Model,” Transaction of the ASAE. Vol.: 43, Issue: 6, pp.
1681-1687, 2000 12 42
XLIII. S. Majundar, and D.S. Jayas, “Classification of cereal grain using machine
vision. IV. Combined morphology, colour and texture model,” Transaction of
the ASAE. Vol.: 43, Issue: 6, pp. 1689-1694, 2000 13 43
XLIV. Suharjito, Bahtiar Imran and Abba Suganda Girsang, “Family relationship
identification by using Extract Features of Gray Level Co-occurrence Matrix
(GLCM) Based on Parents and Children Fingerprint,” International Journal of
Electrical and Computer Engineering, Vol.: 7, Issue: 5, pp. 2738-2745, 2017
36 44
XLV. Wan Nur Hafsha Wan Kairuddin and Wan Mahani Hafizah Wan
Mahmud,“Texture feature analysis for different resolution level of kidney
ultrasound images,” International Research and Innovation Submit
(IRIS2017). IOP Conf. Series: Material Science and Engineering 226, pp. 1-
9, 2017 37 45
XLVI. Yudong Zhang, Shuihua Wang, and Genlin Ji, “Fruit classification using
computer vision and feed forward neural network,” Journal of Food
Engineering. Vol.: 143, pp. 167-177, 2014 28 46

View Download