Publication:
Durian Detection And Counting System Using Deep Learning

Simple item page
cris.virtual.departmentUniversiti Sains Islam Malaysia
cris.virtual.departmentUniversiti Sains Islam Malaysia
cris.virtual.departmentUniversiti Sains Islam Malaysia
cris.virtual.departmentUniversiti Sains Islam Malaysia
cris.virtual.orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.departmentea2c4a28-33df-4ab7-90c4-ee192f82275c
cris.virtualsource.department1c8de4a2-17aa-47e7-b8ee-418339a9953f
cris.virtualsource.department95aab6c1-de74-401f-b5ea-2d728cdff473
cris.virtualsource.departmentdf4b79b3-ae32-42ed-82b6-d38078e51646
cris.virtualsource.orcid95aab6c1-de74-401f-b5ea-2d728cdff473
cris.virtualsource.orcidea2c4a28-33df-4ab7-90c4-ee192f82275c
cris.virtualsource.orcid1c8de4a2-17aa-47e7-b8ee-418339a9953f
cris.virtualsource.orciddf4b79b3-ae32-42ed-82b6-d38078e51646
dc.contributor.authorAmir Hilmi Ahmad Azizien_US
dc.contributor.authorFauzan Abdullah Ashaiman
dc.contributor.authorMus’ab Sahrim
dc.contributor.authorIzzudin Mat Lazimen_US
dc.contributor.authorAzween Mohd Rozmien_US
dc.contributor.authorWan Zakiah Wan Ismail
dc.contributor.authorJuliza Jamaludin
dc.contributor.authorIrneza Ismail
dc.contributor.authorSharma Roa Balakhrisnanen_US
dc.date.accessioned2024-05-28T06:51:40Z
dc.date.available2024-05-28T06:51:40Z
dc.date.issued2023
dc.date.submitted2023-11-6
dc.descriptionIndexed by Scopus/ERA/MyCite
dc.description.abstractArtificial intelligence (AI) and computer vision (CV) advancements have paved the way for more efficient agricultural activities such as predicting and estimating fruit yield. Durian, a fruit native to tropical regions, necessitated using high-tech solutions to keep up with its rising global demand. This work aimed to apply the image analysis technique using deep learning to identify and estimate the number of durian fruits using image recognition. A new dataset was specifically constructed in this work, consisting of 500 images split for training and testing the object detection model. Various pre-trained object detection models such as YOLOv3, YOLOv4, YOLOv3 tiny, and YOLOv4 tiny are used for performance comparison on the newly constructed dataset. The best model is then chosen as the inference model for the drone-captured video dataset, assisted by the DeepSORT algorithm as the counting mechanism. Our investigations showed that the YOLOv4 model significantly performs best among all four state-of-art detection networks where it computes the highest mean average precision (mAP) performance with 96.02% accuracy on the constructed dataset. This work enables more efficient and precise durian cultivation with less labour and higher-quality yields.en_US
dc.identifier.epage2477
dc.identifier.issn1823-4690
dc.identifier.issue5
dc.identifier.spage2470
dc.identifier.urihttps://jestec.taylors.edu.my/Vol%2018%20Issue%205%20October%202023/18_5_14.pdf
dc.identifier.urihttps://oarep.usim.edu.my/handle/123456789/7866
dc.identifier.volume18
dc.language.isoen_USen_US
dc.publisherTaylor’s University, Malaysiaen_US
dc.relation.ispartofJournal of Engineering Science and Technologyen_US
dc.subjectAgriculture, Artificial intelligence, Computer vision, Image analysis, Tropical fruiten_US
dc.titleDurian Detection And Counting System Using Deep Learningen_US
dc.typeArticleen_US
dspace.entity.typePublication
oairecerif.author.affiliation#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliationUniversiti Sains Islam Malaysia
oairecerif.author.affiliation#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliationUniversiti Sains Islam Malaysia
oairecerif.author.affiliationUniversiti Sains Islam Malaysia
oairecerif.author.affiliationUniversiti Sains Islam Malaysia
oairecerif.author.affiliation#PLACEHOLDER_PARENT_METADATA_VALUE#

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Durian Detection And Counting System Using Deep Learning.pdf
Size:
349.84 KB
Format:
Adobe Portable Document Format
Download

Collections

Indexed Publication