Use of Deep Learning and k-Nearest Neighbor Algorithms for Recognition of Fruit Types

M Burhanis Sulthan; Fiqih Rahman Hartiansyah; Aqid Fahri Hafin

doi:10.36564/njca.v10i1.293

Use of Deep Learning and k-Nearest Neighbor Algorithms for Recognition of Fruit Types

M Burhanis Sulthan, Fiqih Rahman Hartiansyah, Aqid Fahri Hafin

Abstract

fruit recognition was done in this research specifically for fruit image. The recognition of fruit in this study can be implemented to know the number of fruits that exist. Fruit image trained into several labels (fruit types) that are classified by data testing. There are several processes and methods undertaken in this research until the classification process, one of this i.e. Gaussian filter to improve the quality of fruit image recognition. Furthermore, the feature extraction process uses Gabor filter and for feature selection, PCA technic is respectively used to select some of the best features. The selected feature will be classified using deep learning and k-nearest neighbor (k-NN) method. Moreover, the results of the processes done carried out in achieving an accuracy of 95.01%.

Keywords

fruit recognition, deep learning, k-nearest neighbor (k-NN), Gaussian filter, Gabor filter, principal component analysis.

Full Text:

PDF

References

W. Zhang et al., “Deep-learning-based in-field citrus fruit detection and tracking,” Hortic. Res., vol. 9, no. March 2021, 2022, doi: 10.1093/hr/uhac003.

D. N. V. S. L. S. Indira, J. Goddu, B. Indraja, V. M. L. Challa, and B. Manasa, “A review on fruit recognition and feature evaluation using CNN,” Mater. Today Proc., no. xxxx, pp. 1–6, 2021, doi: 10.1016/j.matpr.2021.07.267.

J. Lu and N. Sang, “Detecting citrus fruits and occlusion recovery under natural illumination conditions,” Comput. Electron. Agric., vol. 110, pp. 121–130, 2015, doi: 10.1016/j.compag.2014.10.016.

A. Koirala, K. B. Walsh, Z. Wang, and C. McCarthy, “Deep learning – Method overview and review of use for fruit detection and yield estimation,” Comput. Electron. Agric., vol. 162, no. January, pp. 219–234, 2019, doi: 10.1016/j.compag.2019.04.017.

W. Widyawati and R. Febriani, “Real-time detection of fruit ripeness using the YOLOv4 algorithm,” Tek. J. Sains dan Teknol., vol. 17, no. 2, p. 205, 2021, doi: 10.36055/tjst.v17i2.12254.

M. Omid, M. Khojastehnazhand, and A. Tabatabaeefar, “Estimating volume and mass of citrus fruits by image processing technique,” J. Food Eng., vol. 100, no. 2, pp. 315–321, 2010, doi: 10.1016/j.jfoodeng.2010.04.015.

D. M. Bulanon, T. F. Burks, and V. Alchanatis, “Study on temporal variation in citrus canopy using thermal imaging for citrus fruit detection,” Biosyst. Eng., vol. 101, no. 2, pp. 161–171, 2008, doi: 10.1016/j.biosystemseng.2008.08.002.

H. Kuang, C. Liu, L. L. H. Chan, and H. Yan, “Multi-class fruit detection based on image region selection and improved object proposals,” Neurocomputing, vol. 283, pp. 241–255, 2018, doi: 10.1016/j.neucom.2017.12.057.

A. D. M. Africa, “Ripe Fruit Detection and Classification using Machine Learning,” Int. J. Emerg. Trends Eng. Res., vol. 8, no. 5, pp. 1845–1849, 2020, doi: 10.30534/ijeter/2020/60852020.

R. M. Alonso-Salces, C. Herrero, A. Barranco, L. A. Berrueta, B. Gallo, and F. Vicente, “Classification of apple fruits according to their maturity state by the pattern recognition analysis of their polyphenolic compositions,” Food Chem., vol. 93, no. 1, pp. 113–123, 2005, doi: 10.1016/j.foodchem.2004.10.013.

J. Blasco, N. Aleixos, J. Gómez-Sanchís, and E. Moltó, “Recognition and classification of external skin damage in citrus fruits using multispectral data and morphological features,” Biosyst. Eng., vol. 103, no. 2, pp. 137–145, 2009, doi: 10.1016/j.biosystemseng.2009.03.009.

S. I. Saedi and H. Khosravi, “A deep neural network approach towards real-time on-branch fruit recognition for precision horticulture,” Expert Syst. Appl., vol. 159, p. 113594, 2020, doi: 10.1016/j.eswa.2020.113594.

J. Jhawar, “Orange Sorting by Applying Pattern Recognition on Colour Image,” Phys. Procedia, vol. 78, no. December 2015, pp. 691–697, 2016, doi: 10.1016/j.procs.2016.02.118.

P. Wan, A. Toudeshki, H. Tan, and R. Ehsani, “A methodology for fresh tomato maturity detection using computer vision,” Comput. Electron. Agric., vol. 146, no. January, pp. 43–50, 2018, doi: 10.1016/j.compag.2018.01.011.

H. Mureşan and M. Oltean, “Fruit recognition from images using deep learning,” Acta Univ. Sapientiae, Inform., vol. 10, no. 1, pp. 26–42, 2018, doi: 10.2478/ausi-2018-0002.

M. Haghighat, S. Zonouz, and M. Abdel-Mottaleb, “CloudID: Trustworthy cloud-based and cross-enterprise biometric identification,” Expert Syst. Appl., vol. 42, no. 21, pp. 7905–7916, 2015, doi: 10.1016/j.eswa.2015.06.025.

R. S. Choras, “Image Feature Extraction Techniques and Their Applications for CBIR and Biometrics Systems,” Int. J. Biol. Biomed. Eng., vol. 1, no. 1, pp. 6–15, 2007.

T. Li et al., “An improved binocular localization method for apple based on fruit detection using deep learning,” Inf. Process. Agric., no. xxxx, 2021, doi: 10.1016/j.inpa.2021.12.003.

M. B. Sulthan, I. Wahyudi, and L. Suhartini, “Analisis Sentimen Pada Bencana Alam Menggunakan Deep Neural Network dan Information Gain,” J. Apl. Teknol. Inf. dan Manaj., vol. 2, no. 2, pp. 65–71, 2021, doi: 10.31102/jatim.v2i2.1273.

A. Tripathy, A. Agrawal, and S. K. Rath, “Classification of Sentimental Reviews Using Machine Learning Techniques,” Procedia Comput. Sci., vol. 57, pp. 821–829, 2015, doi: 10.1016/j.procs.2015.07.523.

DOI: http://dx.doi.org/10.36564/njca.v10i1.293

DOI (PDF): http://dx.doi.org/10.36564/njca.v10i1.293.g139