Attention-Enhanced YOLO Model via Region of Interest Feature Extraction for Leaf Diseases Detection

Tae-Min Choi; Chang-Hwan Son; Donghyuk Lee

doi:10.14801/jkiit.2021.19.4.83

Attention-Enhanced YOLO Model via Region of Interest Feature Extraction for Leaf Diseases Detection

Recommendations

Search

Questions

잎사귀 질병 검출을 위한 관심 영역 특징 추출 기반의 어텐션 강화 YOLO 모델

Type: Academic journal

Author: Tae-Min Choi (군산대학교) Chang-Hwan Son (군산대학교) Donghyuk Lee (농촌진흥청)

Journal: Korean Institute of Information Technology The Journal of Korean Institute of Information Technology Vol.19 No.4 KCI Accredited Journals

Published: 2021.4

Pages: 83 - 93 (11page)

DOI: 10.14801/jkiit.2021.19.4.83

Usage

📌

Topic

📖

Background

🔬

Method

🏆

Result

Attention-Enhanced YOLO Model via Region of Interest Feature Extraction for Leaf Diseases Detection

Research history (2)

2021

Attention YOLO Model for Leaf Disease Detection

Tae-Min Choi , Chang-Hwan Son Proceedings of KIIT Conference 2021.06 Proceeding

Attention-Enhanced YOLO Model via Region of Interest Feature Extraction for Leaf Diseases Detection

Tae-Min Choi , Chang-Hwan Son , Donghyuk Lee The Journal of Korean Institute of Information Technology 2021.04 Academic journal

Are you curious about the follow-up research of this article?
You can check more advanced research results through related academic papers or academic presentations.
Check the research history of this article

Abstract· Keywords

Report Errors

The YOLO model, which is widely used in the existing object detection, excludes the attention function that can learn which feature vectors are more important. Therefore, in this paper, we propose an attention YOLO model that can improve the object detection performance of the existing YOLO model. The proposed attention model was conceived from the fact that there is no information on diseases in the background area of the input leaf image, and spots and color information that can determine the presence or absence of the diseases exist only inside the leaf. By combining the YOLO"s feature extraction subnetwork with the image segmentation subnetwork capable of dividing the background, leaf, and disease areas from the input leaf, it is intended to improve the ability to distinguish features in the region of interest. In other words, a new attention model that can spatially reinforce the importance of disease-related features in the YOLO model is introduced. In addition, through the experimental results, it is shown that the proposed attention YOLO model can improve the detection performance by about 0.06 in the mean Averaged Precision（mAP) evaluation compared to the existing YOLO model.

#attention YOLO model #object detection #image segmentation #deep convolutional neural networks #smart farm

요약
Abstract
Ⅰ. 서론
Ⅱ. 관련 연구
Ⅲ. 제안한 관심 영역 특징 추출 기반의 어텐션 강화 YOLO 모델
Ⅳ. 실험 및 결과
Ⅴ. 결론
References

References (0)

Add References

If the reference is being serviced by DBpia, please register through [Add Reference]

Recommendations

It is an article recommended by DBpia according to the article similarity. Check out the related articles!

Related Authors

최태민

Affiliation 군산대학교

Fields Engineering > Electrical and Electronic Engineering > Information and Communication Engineering Engineering > Electrical and Electronic Engineering > Electrical Engineering

Articles 8 Usage 1,155

손창환

Affiliation 군산대학교

Fields Engineering > Electrical and Electronic Engineering > Information and Communication Engineering TOP 1% Engineering > Electrical and Electronic Engineering > Electronics Engineering

Articles 79 Usage 7,338

이동혁

Affiliation 국립원예특작과학원

Fields Agriculture and Fishery > Agriculture TOP 10% Agriculture and Fishery > General Agriculture and Fishery

Articles 74 Usage 3,407

Frequently Viewed Together

Image Captioning via Semantic Visual Feature Matching in Heavy Rain Condition

Pung-Hwi Ye , Chang-Hwan Son The Journal of Korean Institute of Information Technology 2021 .05

Developing a Compressed Object Detection Model Based on YOLOv4 for Deployment on Embedded GPU Platform of Autonomous System

Isaac Shim , Ju-Hyung Lim , Young-Wan Jang and others 3 Transaction of the Korean Society of Automotive Engineers 2021 .10

Structure-Aware Residual Network for Rain Streaks Removal

Ju-Chan Kim , Chang-Hwan Son The Journal of Korean Institute of Information Technology 2020 .10

Accessing Impact of DCGAN Image Data Augmentation for CNN based Tomato Disease Classification

Ji-yeon Pa , k , Hyeon-ji Kim Journal of Digital Contents Society 2020 .05

Illuminant-adaptive color reproduction for a mobile display

Jong-Man Kim , Chang-Hwan Son , Sung-Dae Cho and others 1 The Institute of Electronics Engineers of Korea - Signal Processing 2007 .03

Comments(0)

Write first comments.

구분	그룹	데이터 항목
AI 학습용 데이터	원문	원문 PDF 파일
AI 학습용 데이터	원문 + 메타 (기본/상세)	원문 PDF 파일 및 서지정보 CSV
대량 구매용 데이터	B2B 구독 방식	특정 자료 한정으로 원문 접근 권한 부여
대량 구매용 데이터	URL 전달 방식	바로 PDF 뷰어를 열람할 수 있는 URL 제공

구분	그룹	데이터 항목
AI 학습용 데이터	기본 메타	발행기관명, 간행물명, 권호명, 권(vol), 호(issue), 통권, 발행연도, 발행월, 논문명, 저자명, 시작페이지, 종료페이지, 전체페이지, 상세페이지URL
상세 메타 데이터	발행기관 메타	발행기관 이명, 영문명, 창립연도, 홈페이지URL, 발행기관 소개
	간행물 메타	부제목, 간행물 유형, ISSN, ISBN, 최초발행연도, 폐간연도, 간행빈도, 발행주기, 등재사항, 이용수, 피인용수, 권호수, 논문수, 표지이미지
	논문 메타	작성 언어, 부제목, 대등제목, 목차, 키워드, 초록, 이미지, 참고문헌, 이용수, 피인용수, 논문활용도, DBpia통합주제분류, KDC분류, DDC분류, 한국연구재단분류, UCI, DOI
	저자 메타	소속기관, 소속부서, 직급, 연구분야, 연구키워드, 이용수, 피인용수, 저자 논문활용도

구분	그룹	데이터 항목
※ 결합형/맞춤형 메타 데이터는 신청 내용에 따라 다양하게 제공 가능
이용순위 정보	주제분야별 많이 이용된 논문	“인문학”에서 많이 이용된 논문 TOP100
	이용기관별 많이 이용된 논문	“중고등학교”에서 많이 이용된 논문 TOP100
	세부기관별 많이 이용된 논문	“서울대학교”에서 많이 이용된 논문 TOP100
	키워드별 많이 이용된 논문	“Chat GPT”에서 많이 이용된 논문 TOP100
키워드 정보	많이 이용된 키워드	특정기간/분야/저널 내 많이 이용된 키워드
	많이 발행된 키워드	특정기간/분야/저널 내 많이 발행된 키워드
	많이 검색된 키워드	특정기간/분야/저널 내 많이 검색된 키워드
	연구 트렌드 키워드	특정 키워드 연관 연구동향 분석 데이터 키워드

논문 기본 정보

Research history (2)

Abstract· Keywords

AI Summary

Topic

Background

Method

Result

주요내용

Contents

References (0)

Recommendations

Related Authors

Frequently Viewed Together

Recently viewed articles

Comments(0)