Skip to main content
SpringerLink
Log in

Automatic apple grading model development based on back propagation neural network and machine vision, and its performance evaluation

  • Original Article
  • Published:
AI & SOCIETY Aims and scope Submit manuscript

Abstract

This paper describes a new apple classification system based on machine vision and artificial neural network (ANN), which classifies apple in real time on the basis of physical parameters of apple such as size, color and external defects. A specific hardware subsystem has been developed and described for every stage of input and output. The hardware subsystem is interfaced with the software to make the whole system automatic. The purpose of this paper is to automate apple classification. Presently, ANN is used in a wide range of classification applications. We have trained a back-propagation neural network to classify apple. Two sets of variables are used for the training purpose. First set is the independent variable, which is the surface level apple quality parameter. Second set is the dependent variable, which is the quality of the apple. The results of ANN model are discussed; however, the modeling results showed that there is an excellent agreement between the experimental data and predicted values, with a high determination coefficient, very good performance, fewer parameters, shorter calculation time and lower prediction error. The classification accuracy achieved is high, showing that a neural network is capable of making such classification. A low level of errors in classification confirmed that the neural network models are an effective instrument for apple classification. This model might be an alternative method for assessing the quality of apple and provide consumers with a safer food supply.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

Similar content being viewed by others

References

  • Alchanatis V, Peleg K, Ziv M (1993) Classification of tissue culture segments by colour machine vision. JAER 55:299–311

    Article  Google Scholar 

  • Basu JK, Bhattacharyya D, Kim T (2010) Use of artificial neural network in pattern recognition. Int J Softw Eng Appl 4(2):23–32

    Google Scholar 

  • Bhatt AK, Pant D, Singh R (2009) An analysis of the performance of artificial neural network technique for apple classification. AI & Soc J Knowl Culture Commun 24(1). doi:10.1007/s00146-012-0425-z

  • Brosnan T, Sun DW (2004) Improving quality inspection of food products by computer vision: a review. J Food Eng 61:3–16

    Article  Google Scholar 

  • Dickson MA, Bausch WC, Howarth MS (1994) Classification of a broadleaf weed, a grassy weed, and corn using image processing techniques. SPIE 2345:297–305

    Google Scholar 

  • Edwards EJ, Cobb AH (1999) The effect of prior storage on the potential of potato tubers (Solanum tuberosum L.) to accumulate glycoalkaloids and chlorophylls during light exposure, including artificial neural network modelling. J Sci Food Agric 79:1289–1297

    Article  Google Scholar 

  • Farkas I, Remenyi P, Biro A (2000) A neural network topology for modelling grain drying. Comp Electron Agric 26:147–158

    Article  Google Scholar 

  • Gerrard DE, Gao X, Tan J (1996) Beef marbling and color score determination by image processing. J Food Sci 61:145–148

    Article  Google Scholar 

  • Greenwood CS, Chamberlin DW, Gatos L (1973) Apparatus for sorting fruit according to Color, Patent no. 3,770,111, Calif

  • Growe TG, Delwiche MJ (1996) A system for fruit defect detection in real-time. AGENG 96, Paper No. 96F-023

  • Guyer DE, Miles GE, Gaultney LD, Schereiber MM (1993) Application of machine vision to shape analysis in leaf and plant identification. TASAE 36(1):163–171

    Google Scholar 

  • Hussian MA, Shaur M, Ng NW (2002) Predictions of pores formation (porosity) in foods during drying: generic models by the use of hybrid neural network. J Food Eng 51:239–248

    Article  Google Scholar 

  • Jamieson V (2002) Physics raises food standards. Phys World 1:21–22

    Google Scholar 

  • Leemans V, Magein H, Destain MF (1998) Defect segmentation on ‘golden delicious’ apples by using colour machine vision. Comput Electron Agri 20(2):117–130

    Article  Google Scholar 

  • Leemans V, Magein H, Destain MF (1999) Defect segmentation on ‘jonagold’ apples using colour vision and a bayesian classification method. Comput Electron Agri 23(1):43–53

    Article  Google Scholar 

  • Liao K, Paulsen MR, Reid JF (1993) Corn kernel breakage classification by machine vision using a neural network classifier. Trans ASAE 36(6):1949–1953

    Article  Google Scholar 

  • Mathworks Online (2009) Available: http://www.mathworks.com

  • McCulloch W, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5:115–133

    Article  MATH  MathSciNet  Google Scholar 

  • McDonald T, Chen YR (1990) Separating connected muscle tissues in images of beef carcass rib eyes. Trans ASAE 33:2059–2065

    Google Scholar 

  • Miller BK, Delwiche MJ (1991) Peach defect detection with machine vision. TASAE 34(6):2588–2597

    Google Scholar 

  • Moller MF (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw 6:525–533

    Article  Google Scholar 

  • Moltó E, Aleixos N, Ruiz LA, Vázquez J, Juste F (1996), An artificial vision system for fruit quality assessment. AGENG 96, Madrid, Paper No. 96F-078

  • Ni H, Gunasekaran S (1998) Food quality prediction with neural networks. Food Technol 5:60–65

    Google Scholar 

  • Okamura NK, Delwiche MJ, Thompson JF (1991) Raising grading by machine vision. ASAE Paper No. 91-7011. St. Joseph, MI

  • Rigeny MP, Kranzler GA (1989) Seedling classification performance of a neural network, ASAE paper 89-7523, ASAE, St. Joseph, MI 49085-9659

  • Sarkar N, Wolfe RR (1985) Feature extraction techniques for sorting tomatoes by computer vision. Trans ASAE 28(3):970–979

    Article  Google Scholar 

  • Sayeed MS, Whittaker AD, Kehtarnavaz ND (1995) Snack quality evaluation method based on image feature and neural network prediction. Trans ASAE 38(4):1234–1245

    Article  Google Scholar 

  • Sofu A, Ekinci FY (2007) Estimation of storage time of yogurt with artificial neural network modeling. J Dairy Sci 90:3118–3125. doi:10.3168/jds.2006-591

    Article  Google Scholar 

  • Sun DW (2004) Computer vision: an objective, rapid and noncontact quality evaluation tool for the food industry. J Food Eng 61:1–2

    Article  Google Scholar 

  • Suzuki ST, Uesugi YM, Sekinem YM (1977) Automatic sorting conveyor systems. Patent no. 4,031,998, Japan

  • Tao Y, Morrow CT, Heinemann PH, Sommer JH (1990), Automated machine vision inspection of potatoes. ASAE Paper No. 90-3531

  • Tengsater TN, Park T (1977) Apparatus for measuring the internal quality of produce. Patent no. 4,035,636, Md

  • Varghese Z, Morrow CT, Heinemann PH, Sommer HJ, Tao Y, Crassweller RM (1991). Automated inspection of Golden Delicious apples using colour computer vision. ASAE Paper No. 91-7002

  • Wang HH, Sun DW (2002) Assessment of cheese browning affected by baking conditions using computer vision. J Food Eng 56:339–345

    Article  Google Scholar 

  • Zakaria Z, Isa NAM, Suandi SA (2010) A study on neural network training algorithm for multiface detection in static images. World Acad Sci Eng Technol 62

  • Zweiri YH, Whidborne JF, Sceviratne LD (2002) A three-term backpropagation algorithm. Neurocomputing 50:305–318

    Article  Google Scholar 

Download references

Acknowledgments

This research work was fully supported by Department of Science and Technology (science and society division), Government of India, under the scheme for Young Scientist and Professional.

Author information

Authors and Affiliations

  1. Department of Computer Science, Birla Institute of Applied Sciences, Bhimtal, Nainital, Uttarakhand, India

    A. K. Bhatt

  2. Department of Computer Science, Uttarakhand Open University, Dehradun, Uttarakhand, India

    D. Pant

Authors
  1. A. K. Bhatt
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. D. Pant
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to A. K. Bhatt.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Bhatt, A.K., Pant, D. Automatic apple grading model development based on back propagation neural network and machine vision, and its performance evaluation. AI & Soc 30, 45–56 (2015). https://doi.org/10.1007/s00146-013-0516-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00146-013-0516-5

Keywords

Search

Navigation