แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Supanat Jintawatsakoon. Quality assessment of cocoa bean using regression convolutional neural network. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2023.
Quality assessment of cocoa bean using regression convolutional neural network
Name: Seksan Sangsawad
Organization :
Rangsit University. College of Digital Innovation Technology
Email :
seksan.s@rsu.ac.th
Name: Supanat Jintawatsakoon
Organization :
Rangsit University. College of Digital Innovation Technology
Email :
supanat.j@rsu.ac.th
LCSH:
Cocoa processing
Abstract:
The evaluation of cocoa bean quality is essential
for chocolate production. We propose a novel approach for
cocoa bean quality assessment, traditionally reliant on the laborintensive
cut-test method. Our research explores the utilization
of Convolutional Neural Networks (CNNs), specifically the
ResNet V2 152-layer model, to convert the cut-test classification
problem into a regression task. We focus on exploiting the
probabilistic interpretation, class ordering, and the potential
performance benefits offered by regression models. Data
augmentation techniques, including position augmentation and
online data augmentation, are employed to expand our limited
dataset of 100 images per class, each tagged with a quality score.
We evaluate various models, from a base-line model to
ResNet50, both with and without data augmentation, and
ResNetV2 152 with data augmentation. The study shows the
superior performance of ResNet models, especially when
coupled with data augmentation. The best results were achieved
using the ResNetV2 152 model with data augmentation,
indicating the promising potential of sophisticated models and
data augmentation techniques in regression tasks
King Mongkut's University of Technology North Bangkok. Central Library
Address:
BANGKOK
Email:
library@kmutnb.ac.th
Created:
2023
Modified:
2024-04-23
Issued:
2024-04-23
บทความ/Article
application/pdf
BibliograpyCitation :
In Institute of Electrical and Electronics Engineers. The 27th International Computer Science and Engineering Conference 2023 (ICSEC 2023) (pp.335-340). Bangkok : Institute of Electrical and Electronics Engineers
eng
©copyrights King Mongkut's University of Technology North Bangkok
RightsAccess:
ใช้เวลา
0.029677 วินาที
Seksan Sangsawad
| Title | Contributor | Type |
|---|---|---|
| Quality assessment of cocoa bean using regression convolutional neural network
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Seksan Sangsawad;Supanat Jintawatsakoon | บทความ/Article | |
| Performance evaluation of collaborative filtering algorithms on video streaming platform
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Supanat Jintawatsakoon;Seksan Sangsawad | บทความ/Article |
Supanat Jintawatsakoon
| Title | Contributor | Type |
|---|---|---|
| Visual glitches classification for video game using deep learning-based techniques
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Supanat Jintawatsakoon | บทความ/Article | |
| Quality assessment of cocoa bean using regression convolutional neural network
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Seksan Sangsawad;Supanat Jintawatsakoon | บทความ/Article | |
| Performance evaluation of collaborative filtering algorithms on video streaming platform
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Supanat Jintawatsakoon;Seksan Sangsawad | บทความ/Article |