지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2021.4
- 수록면
- 5 - 14 (10page)
- DOI
- 10.7584/JKTAPPI.2021.04.53.2.5
이용수
초록· 키워드
오류제보하기
There are some problems in traditional paper defects classification, such as the poor generalization performance, less types of recognition, and insufficient recognition accuracy. The deep learning method provides a new scheme for paper defects classification. However, due to the small sample size of paper defect images set, the over fitting phenomenon is easy to appear in the training process. Aiming this problem, a transfer learning method based on convolutional neural network model is proposed．Firstly, freezing the first seven construction layers of VGG16 network which has been trained by ImageNet, and fine tune the rest convolution layers with the paper defect images set to complete the feature extraction; Secondly, the full connection layers for classification are improved to meet the needs of paper defects classification; Finally, transfer learning strategy is adopted in the training process to improve the efficiency. The experimental results demonstrate that the paper defects classification proposed in our approach can improve the efficiency and accuracy of paper defects recognition. The approach will beneficial for the web inspection process.
목차
ABSTRACT
1. Introduction
2. Paper Defects Classification Based on VGG16 and Transfer Learning
3. Data Acquisition and Preprocessing
4. Results and Discussion
5. Conclusions
Literature Cited
참고문헌 (17)
참고문헌 신청
Yun-hui Qu / 2020 / Web Inspection Algorithm for Low Contrast Paper Defects Based on Artificial Bee Colony Optimization / 펄프종이기술 52(2):43~51
Yun-hui Qu / 2020 / An Algorithm for On-Line Image Segmentation of Multiple Paper Defects Based on Fast Two-Dimensional Threshold Method / 펄프종이기술 52(4):28~37
Wen-juan Shan / 2019 / Multivariable Dimension-reduction and Synergic Control Strategy for Cross-directional Basis Weight of Papermaking Process / 펄프종이기술 51(2):76~87
Wu, G. A. / 2016 / Application of industrial camera on paper making / paper and paper making 35(07):8~16
Tang, W. / 2020 / Review of advanced control technologies and modern control systems for paper industry / China Pulp & Paper 39(8):14~25
Yun-hui Qu / 2020 / An Algorithm for On-Line Image Segmentation of Multiple Paper Defects Based on Fast Two-Dimensional Threshold Method / 펄프종이기술 52(4):28~37
Wen-juan Shan / 2019 / Multivariable Dimension-reduction and Synergic Control Strategy for Cross-directional Basis Weight of Papermaking Process / 펄프종이기술 51(2):76~87
Wu, G. A. / 2016 / Application of industrial camera on paper making / paper and paper making 35(07):8~16
Tang, W. / 2020 / Review of advanced control technologies and modern control systems for paper industry / China Pulp & Paper 39(8):14~25
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Paper Defects Recognition Based on Deformable Convolution
펄프·종이기술
2022 .04
-
An Algorithm for On-Line Image Segmentation of Multiple Paper Defects Based on Fast Two-Dimensional Threshold Method
펄프·종이기술
2020 .08
-
Web Inspection Algorithm for Low Contrast Paper Defects Based on Artificial Bee Colony Optimization
펄프·종이기술
2020 .04
-
Identification and Detection of Surface Defects of Outer Package Printed Matter Based on Machine Vision
펄프·종이기술
2020 .04
-
Basic research for improving the production of blood cockle : Work efficiency and defects in the processing methods
한국수산과학회 양식분과 학술대회
2016 .05
-
딥러닝(VGG16) 모델 구축을 통한 자생식물 13종 종자 이미지 분류 및 Grand-CAM 기반 분류 특징 분석
한국잡초학회 별책(학술대회 초록집)
2024 .10
-
제조 공정에서의 실시간 불량 탐지를 위한 딥러닝 모델 적용 연구 - 라벨 인쇄 공정에서 불량 탐지 사례 -
펄프·종이기술
2021 .10
-
Convolutional Neural Network Technique for Distinguishing Nine Varieties of Vegetable Crops
농업생명환경연구
2024 .06
-
소규모 저수지의 특성을 고려한 제체 안전진단의 정량적 상태평가 기준 개선
한국농공학회논문집
2021 .09
-
Feature Extraction for Germination Image Classification of Pear Pollen by Random Forest and Convolutional Neural Network Models
한국원예학회 학술발표요지
2020 .11
-
Classification of Lettuce Varieties based on Machine Learning
한국원예학회 학술발표요지
2023 .05
-
Morphological classification of mosquitoes using deep learning
한국농약과학회 학술발표대회 논문집
2018 .10
-
말벌 영상인식을 위한 심층 합성곱 신경망의 성능 평가
Journal of Apiculture
2019 .09
-
Quality grading of Hanwoo (Korean native cattle breed) sub-images using convolutional neural network
Korean Journal of Agricultural Science
2020 .12
-
Estimation of tomato maturity as a continuous index using deep neural networks
Korean Journal of Agricultural Science
2022 .12
-
합성곱 신경망을 이용한 ‘미황’ 복숭아 과실의 성숙도 분류
생물환경조절학회지
2022 .10
-
해양시설 용어 정의 및 분류 체계에 관한 일고찰
수산해양교육연구
2017 .06
-
The Study on the Classification of Liquid Formulations for the Elderly
한국식품영양과학회 학술대회발표집
2022 .10
-
식물성 식품에 대한 코덱스 식품 분류
식품과학과 산업
2023 .03
-
Discriminant analysis of grain flours for rice paper using fluorescence hyperspectral imaging system and chemometric methods
Korean Journal of Agricultural Science
2020 .09
이 논문의 저자 정보
이 논문과 함께 이용한 논문
Sequential Modeling of Paper Drying Process to Reduce Thermal Energy Use, Part 2: Simulation Results
Lingbo Kong
,
Jiahao Li
,
Ziliang Zhang
펄프·종이기술
2022
.10
ResNet50을 이용한 냉연강판에서의 표면결함 자동분류
최원준
,
김윤수
,
조정원
외 5명
한국정보과학회 학술발표논문집
2021
.12
지류 포장재의 차단 특성에 따른 재활용성 평가
이용주
,
임동건
,
손유빈
외 3명
펄프·종이기술
2021
.12
수입 펄프 가격의 시계열적 특성 분석
김선웅
,
이석일
,
윤병삼
펄프·종이기술
2021
.12
Establishment of NOx Concentration Model at the Outlet of SCR Denitrification System for Alkali Recovery Furnace Flue Gas Based on Improved LSSVM
Yan Li
,
Zhen Hu
,
Binbin He
외 1명
펄프·종이기술
2021
.10
최근 본 자료
댓글(0)
0