Image based durian (Durie azomethines Linn) sweetness measurement by ResNet50

Article Sidebar

PDF
Published: Feb 21, 2024
Keywords:
Convolutional neural network Pattern recognition ResNet50 Sweetness measurement

Main Article Content

Chomtip Pornpanomchai
Faculty of Information and Communication Technology, Mahidol University, Nakhon Phathom 13170, Thailand

Abstract

Development of the capability to determine durian sweetness using a single image is the main objective of this research. The developed system is called the “Durian Sweetness Measurement System” or DSMS. The DSMS employed ResNet50 in the MATLAB toolbox to recognize durian imagery. The system consists of four main subprograms, 1) durian dataset creation, 2) image acquisition, 3) durian sweetness evaluation, and 4) results illustration. The system was used to conduct experiments on 17 Monthong durian pulps in 102 video clips. The DSMS determined that sweetness of the raw, mature and ripe durian was around 14–19, 20–26 and 27–31 oBrix, respectively. The accuracy of the DSMS is 97.57%, with an average access time of 1.5248 sec per image.

Article Details

How to Cite
Pornpanomchai, C. (2024). Image based durian (Durie azomethines Linn) sweetness measurement by ResNet50. Engineering and Applied Science Research, 51(2), 200–210. Retrieved from https://ph01.tci-thaijo.org/index.php/easr/article/view/254034
Issue
Vol. 51 No. 2 (2024)
Section
ORIGINAL RESEARCH
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

References

Chua JY, Pen KM, Poi JV, Ooi KM, Yee KF. Upcycling of biomass waste from durian industry for green and sustainable applications: an analysis review in the Malaysia context. Energy Nexus. 2023;10:1-21.

Mursyidin DH, Makruf MI, Badruzsaufari, Noor A. Molecular diversity of exotic durian (Durio spp.) germplasm: a case study of Kalimantan, Indonesia. J Genet Eng Biotechnol. 2022;20(1):1-13.

Tagubase JL, Palangga Z, Liu H, Araki T, Ueno S, Yoshie Y. Sensory evaluation of frozen-thawed indigenous Philippine durian cultivars and its association to measured quality attributes. Transactions of the Japan Society of Refrigerating and Air Conditioning Engineers. 2018;35(3):261-7.

Glasier G. 31 Thai fruits to try in Thailand (with seasonality chart) [Internet]. Bangkok: Chef Travel Guide; 2023 [cited 2023 Jul 19]. Available from: https://cheftravelguide.com/thai-fruits/.

Likhitpichitchai P, Khermkhan J, Kuhaswonvetch S. The competitiveness of Thai durian export to China’s market. GMSARN Int J. 2023;17:371-8.

Deethong T, Boonnam N. Forecasting analysis of the durian yield trends in Southern Thailand using Holt-Winters exponential smoothing method and Box-Jenkins’ techniques. Proceeding of the 5th ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (NCON); 2022 Jan 26-28; Chiang Rai, Thailand: USA: IEEE; 2022. p. 29-32.

Wiangsamut B, Wiangsamut MEL. Assessment of natural fruit ripening and fruit quality of three elite durian cultivars for overland export. Trends Sci. 2023;20(5):1-11.

Xiao Z, Niu M, Niu Y. Comparative study on volatile compounds and taste components of different durian cultivars based on GC-MS, UHPLC, HPAEC-PAD, E-Tongue and E-Nose. Molecules. 2022;27(4):1-12.

Sangpong L, Khaksar G, Pinsorn P, Oikawa A, Sasaki R, Erban A, et al. Assessing dynamic changes of taste-related primary metabolism during ripening of durian pulp using metabolomic and transcriptomic analyses. Front Plant Sci. 2021;12:1-14.

Sirikantaramas S, Sangpong L, Khaksar G, Pinsorn P, Oikawa A, Sasaki R, et al. Assessing dynamic changes in flavor-related compounds during durian fruit ripening using metabolome and transcriptome analyses. Research Square. 2021:1-24.

Pokhrel DR, Sirisomboon P, Khurnpoon L, Posom J, Saechua W. Comparing machine learning and PLSDA algorithms for durian pulp classification using inline NIR spectra. Sensors 2023;23(11):1-22.

Sharma S, Sirisomboon P, Sumesh KC, Terdwongworakul A, Phetpan K, Kshetri TB, et al. Near-infrared hyperspectral imaging combined with machine learning for physicochemical-based quality evaluation of durian pulp. Postharvest Biol Technol. 2023;200:1-14.

Cheepsomsong T, Sangwanangkul P, Puttipipatkajorn A, Terdwongworakul A, Puttipipatkajorn A, Kulmutiwat S, et al. Multi-parameter index for durian maturity and its prediction using miniature near-infrared spectrometer. Postharvest Biol Technol. 2023;205:1-7.

Ditcharoen S, Sirisomboon P, Saengprachatanarug K, Phuphaphud A, Rittiron R, Terdwongworakul A, et al. Improving the non-destructive maturity classification model for durian fruit using near-infrared spectroscopy. Artif Intell Agric. 2023;7:35-43.

Tan XY, Misran A, Whye CK, Daim LDJ, Ding P, Dek MSP. Postharvest quality indices of different durian clones at ripening stage and their volatile organic compounds. Sci Hortic. 2020;264:1-13.

Prasetia HA, Budiawan S, Syahputra A, Umiarsih R, Pangastuweni R, Fauzidaty MR, et al. Effects of freezing time on degradation of durian (Durio zibethinus Murr.) fruit’s attributes during the frozen storage. Trop Life Sci Res. 2023;34(1):19-39.

Arsa S, Wipatanawin A, Suwapanich R, Makkerdchoo O, Chatsuwan N, Kaewthong P, et al. Properties of different varieties of durian. Appl Sci. 2021;11912):1-19.

Niponsak A, Laohakunjita N, Kerdchoechuena O, Wongsawadeeb P. Uthairatanakija A. Novel ripeness label based on starch/chitosan incorporated with pH dye for indicating eating quality of fresh–cut durian. Food Control. 2020;107:1-8.

Thipsrirach Y, Kosacka-Olejnik M, Poonikom K. Classification of durian maturity using a convolutional neural network. Eng Appl Sci Res. 2023;50(3):233-43.

Uy JN, Villaverde JF. A durian variety identifier using Canny edge and CNN. The 7th International Conference on Control Science and Systems Engineering (ICCSSE); 2021 July 30 – Aug 1; Qingdao, China. USA: IEEE; 2021. p. 293-97.

Lim MG, Chuah JH. Durian types recognition using deep learning techniques. The 9th IEEE Control and System Graduate Research Colloquium (ICSGRC); 2018 Aug 3-4; Shah Alam, Malaysia. USA: IEEE; 2018. p. 183-7.

Serpen JY. Comparison of sugar content in bottled 100% fruit juice versus extracted juice of fresh fruit. Food Sci Nutr. 2012; 3(11):1509-13.

Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data. 2021;8(55):1-74.

Ittatirut T, Lekhalawan A, Tangjitwattanakorn W, Pornpanomchai C. Apple sweetness measurement by image processing technique. The 5th ICT International Student Project Conference (ICT-ISPC); 2016 May 27-28; Nakhon Phathom, Thailand. USA: IEEE; 2016. p. 1-4.

Chomtip P, Adhisaya V, Kanhokthorn L, Phoptorn L. Banana (Musa Acuminata Triploid AAA, Cavendish) sweetness measurement by digital image processing technique. International Journal of Design, Analysis & Tools for Integrated Circuits & Systems. 2018;7(1):34-7.