Abstract
Presently fruits are sorted into quality categories manually in majority of the packing lines. Nonetheless, manual sorting is associated with various problems such as low accuracy, subjectivity, inconsistency and is not indorsed for export quality fruits. Hence, a computational facility provided with a machine vision system is required in the sorting process. The aim of present paper is to design and develop a non-destructive method to sort pomegranate fruits employing wavelet features and artificial neural network (ANN). Pomegranate fruits are sorted into two classes: diseased and healthy. Firstly, images of fruits are acquired from a local fruit market. Histogram equalization is applied followed by wavelet denoising. Total of 252 wavelet features are extracted. Experimentations are conducted to train ANN. Performance of the network is established based on seven performance metrics. The results of experimentation revealed that the performance of ANN is satisfactory with an accuracy of 91.3%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Deepa, P., and S. N. Geethalakshmi: Improved watershed segmentation for apple fruit grading. In: International Conference on Process Automation, Control and Computing (PACC), IEEE (2011).
Nandi, C. S., B. Tudu, and C. Koley: Machine Vision Based Techniques for Automatic Mango Fruit Sorting and Grading Based on Maturity Level and Size. Sensing Technology: Current Status and Future Trends II, pp. 27–46. Springer International Publishing (2014).
Teimouri, Nima, et al: A novel artificial neural networks assisted segmentation algorithm for discriminating almond nut and shell from background and shadow. Computers and Electronics in Agriculture 105, 34–43 (2014).
Font, D., et al: An image processing method for in-line nectarine variety verification based on the comparison of skin feature histogram vectors. Computers and Electronics in Agriculture 102, 112–119 (2014).
Clement, Javier, et al: An active contour computer algorithm for the classification of cucumbers. Computers and Electronics in Agriculture 92, 75–81 (2013).
Dua, Sumeet, et al: Wavelet-based energy features for glaucomatous image classification. IEEE Transactions on Information Technology in Biomedicine 16.1, 80–87 (2012).
Ghazali, Kamarul Hawari, et al: Feature extraction technique using discrete wavelet transform for image classification. In: SCOReD 2007. 5th Student Conference on. IEEE (2007).
Al Ohali, Yousef: Computer vision based date fruit grading system: Design and implementation. Journal of King Saud University-Computer and Information Sciences 23.1, 29–36 (2011).
Rocha, Anderson, et al: Automatic fruit and vegetable classification from images. Computers and Electronics in Agriculture 70.1, 96–104 (2010).
Hazra, Tapan Kumar, Rajib Guhathakurta: Comparing Wavelet and Wavelet Packet Image Denoising Using Thresholding Techniques. International Journal of Science and Research 5.6, 790–796 (2016).
Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins.: Digital Image Processing. Pearson Education, India (2009).
Plotting and Intrepretating an ROC Curve, http://gim.unmc.edu/dxtests/roc2.htm.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix-A: Performance Parameters for Wavelet Features
Appendix-A: Performance Parameters for Wavelet Features
Iteration | TP | FN | FP | TN | Se | Sp | Ac | PPV | NPV | MSE |
|---|---|---|---|---|---|---|---|---|---|---|
1 | 54 | 9 | 8 | 46 | 0.86 | 0.85 | 85.5 | 0.87 | 0.83 | 0.1159 |
2 | 59 | 6 | 3 | 49 | 0.9 | 0.94 | 92.3 | 0.95 | 0.89 | 0.0686 |
3 | 58 | 3 | 4 | 52 | 0.95 | 0.92 | 94.0 | 0.93 | 0.94 | 0.0708 |
4 | 58 | 14 | 4 | 41 | 0.8 | 0.91 | 84.6 | 0.93 | 0.74 | 0.1074 |
5 | 59 | 5 | 3 | 50 | 0.92 | 0.94 | 93.2 | 0.95 | 0.90 | 0.0562 |
6 | 62 | 4 | 0 | 51 | 0.94 | 1.0 | 96.6 | 1 | 0.92 | 0.0288 |
7 | 59 | 5 | 3 | 50 | 0.92 | 0.94 | 93.2 | 0.95 | 0.90 | 0.0591 |
8 | 59 | 4 | 3 | 51 | 0.93 | 0.94 | 94.0 | 0.95 | 0.92 | 0.0554 |
9 | 53 | 1 | 9 | 54 | 0.98 | 0.85 | 91.5 | 0.85 | 0.98 | 0.0866 |
10 | 55 | 7 | 7 | 48 | 0.88 | 0.87 | 88.0 | 0.88 | 0.87 | 0.0874 |
Average values | 0.91 | 0.91 | 91.3% | 0.92 | 0.89 | 0.0736 | ||||
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Arun Kumar, R., Rajpurohit, V.S. (2019). Wavelet Features for Pomegranate Sorting Using Machine Vision. In: Saini, H., Sayal, R., Govardhan, A., Buyya, R. (eds) Innovations in Computer Science and Engineering. Lecture Notes in Networks and Systems, vol 32. Springer, Singapore. https://doi.org/10.1007/978-981-10-8201-6_20
Download citation
DOI: https://doi.org/10.1007/978-981-10-8201-6_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-8200-9
Online ISBN: 978-981-10-8201-6
eBook Packages: EngineeringEngineering (R0)