Image based durian (Durie azomethines Linn) sweetness measurement by ResNet50
Issued Date
2024-01-25
Resource Type
ISSN
25396161
eISSN
25396218
Scopus ID
2-s2.0-85194368205
Journal Title
Engineering and Applied Science Research
Volume
51
Issue
2
Start Page
200
End Page
210
Rights Holder(s)
SCOPUS
Bibliographic Citation
Engineering and Applied Science Research Vol.51 No.2 (2024) , 200-210
Suggested Citation
Pornpanomchai C. Image based durian (Durie azomethines Linn) sweetness measurement by ResNet50. Engineering and Applied Science Research Vol.51 No.2 (2024) , 200-210. 210. doi:10.14456/easr.2024.20 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/98599
Title
Image based durian (Durie azomethines Linn) sweetness measurement by ResNet50
Author(s)
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
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 27–31oBrix, respectively. The accuracy of the DSMS is 97.57%, with an average access time of 1.5248 sec per image.