Comparison the Performance of Models for Classifying Thai Exported Fruit Images

Main Article Content

Walaiporn Sornkliang
Woraphat Jaihao
Prumrapee Thongkaew
Thanabdin Hemtanon
Pichayut Srinuankaew1
Kritaphat Songsri-in

Abstract

Fruits are a major economic crop in Thailand, providing both primary employment and income for many farmers. This research aims to develop and evaluate the performance of a classification model for Thai export fruits. A dataset of over 710 images of Thai export fruits was collected. The model learning process consists of two steps: dimensionality reduction of image data and model learning. In the dimensionality reduction step, two methods were experimented with: image squashing and convolutional neural network. The models studied in the second step consisted of three models: the nearest neighbor model, the decision tree model, and the logistic regression model. The research results on the collected dataset found that the image classification performance of Thai export fruits using dimensionality reduction techniques with convolutional neural networks is higher than that of image flattening, and the model that can best classify images is the logistic regression model, which achieves a maximum accuracy and recall of 95.21%, a precision at 95.50%, F1 score at 95.16%. It used the most training time of 25.809 seconds but only took 7.70 milliseconds for inference.

Article Details

How to Cite
Sornkliang, W., Jaihao, W. ., Thongkaew, P. ., Hemtanon, T. ., Srinuankaew1, P. ., & Songsri-in, K. (2024). Comparison the Performance of Models for Classifying Thai Exported Fruit Images. Journal of Applied Informatics and Technology, 7(1), 73–90. Retrieved from https://ph01.tci-thaijo.org/index.php/jait/article/view/255424
Section
Research Article

References

Abadi, M. et al. (2016). Tensorflow: a system for large-scale machine learning. Proceeding of the 12th USENIX Conference on Operating Systems Design and Implementation, Savannah GA, USA, November 2-4, 2016, 265–283. https://www.usenix.org/conference/osdi16/technical-sessions/presentation/abadi

Chotichatmala, S. & Wiwatwattana, N. (2021). Machine learning-based one-class fruit classification models for apple images detection. Proceeding of the 1st Data Science Conference, Bangkok, Thailand, 2021, 16-20. http://ir-ithesis.swu.ac.th/dspace/handle/123456789/1085 [In Thai]

Chuchip, K. (2018). Remote Sensing Technical Note No.5 : Logistic Regression. Faculty of Forestry, Kasetsart

University. [In Thai]

Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database.

In 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 248-255. https://doi.org/10.1109/CVPR.2009.5206848

He, K., Zhang, X., Ren, S. & Sun, J. (2016). Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770-778. IEEE. https://doi.org/10.1109/CVPR.2016.90

Klodpeng, J. (2023). Fruit classification system. Center for Agricultural Technology and Innovation, Bank for Agriculture and Agricultural Cooperatives, Naresuan University. Retrieved 5 November 2023. Retrieved from https://www.gosmartfarmer.com/innovation/21350. [In Thai]

Kummong, R. (2021). Mangosteen detection using deep learning. Information Technology Journal, 18(1), 47-55. [In Thai]

Office of Agricultural Economics. (2023). Thailand’s database system and foreign agricultural trade information services. Retrieved 15 November 2023. Retrieved from https://impexpth.oae.go.th. [In Thai]

Pakamwang, j., Khoomsab, K., & Srimuang, W. (2020). Model comparisons of classification for tourism development of Khao Kho district, Phetchabun Province using data mining techniques. Rajabhat Journal of Sciences Humanities & Social Sciences, 21(1), 213-223. https://ph01.tci-thaijo.org/index.php/psru/article/view/240641 [In Thai]

Pedregosa, F. et al. (2011). Scikit-learn: machine learning in Python. Journal of Machine Research, 12, 2825–2830. https://dl.acm.org/doi/10.5555/1953048.2078195

Sereepong, C. & Wiwatwattana, N. (2021). Coffee bean quality classification using convolutional neural network. Proceeding of the 1st Data Science Conference, Bangkok, Thailand, 2021, 74-85. [In Thai]

Suksukont, A., Santingamwong, C., Khamkhaek, W., & Pansuwan, S. (2022). Fruits ripening analysis system using image processing technology. Journal of Information Science and Technology, 12(1), 61-66. https://doi.org/10.14456/jist.2022.6 [In Thai]

Utanon, W., Phongsuphap, S., Sawangarom, W., & Singkleewan, N. (2020). Non-destructive image processing technique and rule-based classification in estimating the quality of fruit. Journal of Information, 19(1), 130-138. [In Thai]