Wood Species Classification using Convolutional Neural Networks and Analysis of the Factors Influencing Their Classification Performance
저자
발행사항
춘천 : 강원대학교 대학원, 2024
학위논문사항
학위논문(박사)-- 강원대학교 대학원 : 산림바이오소재공학과 2024. 2
발행연도
2024
작성언어
영어
주제어
발행국(도시)
강원특별자치도
형태사항
127 ; 26 cm
일반주기명
지도교수: 김남훈
UCI식별코드
I804:42002-000000034004
소장기관
This study investigated a method for classifying wood species more easily and accurately based on convolutional neural networks (CNNs) for detecting illegally traded timbers that are imported into Korea through illegal logging, CITES-Listed species, and other abnormal routes. Anatomical features have been widely used to classify wood species, and the International Association of Wood Anatomists has standardized the species classification procedure by establishing anatomical feature classification guidelines for hardwood (1989), softwood (2004), and bark (2016). In this study, to classify commercial wood species using CNNs, the datasets were constructed using following samples: 1) ten softwood species widely used as commercial species in Korea; 2) six Quercus wood species distributed widely in Korea; and 3) the barks of seven Quercus species, including six domestic species and Quercus suber imported from Portugal for cork production. The performance of the CNNs in species classification and the factors affecting classification performance were analyzed. In Chapter 1, the main background of this study, including the global environmental crisis, the importance of forest resources, and the conservation and use of wood resources, is explained. In addition, the academic development of related fields and current research trends are investigated by reviewing the academic history of plant anatomy, wood anatomy, and wood identification, from the invention of the first microscope in the 17th century to the present day. Furthermore, the history of the introduction of artificial intelligence technology in the field of wood species identification and recent ongoing studies are explained. In Chapter 2, the classification performance and factors affecting species classification performance using a dataset of cross-sections of the ten softwood species and four types of architectures based on CNNs were investigated. The four architectures showed a high classification accuracy of over 90% between species, and the accuracy increased with increasing epochs. However, the starting points of the accuracy, loss, and training speed increments differed according to the architecture. The latewood dataset showed the highest accuracy. The epochs and augmented datasets also positively affected accuracy, whereas the whole part and non-augmented datasets had a negative effect on accuracy. Additionally, the augmented dataset tended to derive stable results and reached the convergence point earlier. The augmented latewood dataset was the most important factor affecting the classification performance and should be used for training CNNs. In Chapter 3, the classification performance and factors affecting species classification performance using a dataset of cross-sections of the six Quercus species and a CNN architecture were investigated. The analysis of the average classification accuracy of the final five epochs revealed no significant difference in classification accuracy depending on the dataset between the whole part and the earlywood part. However, the model learned with augmented dataset yielded significantly superior results in classification accuracy compared to the model learned with the non-augmented dataset. The classification accuracy according to the optimizer did not show a significant difference among the SGD, Adam, and RMSProp. In the analysis based on the final 5 epochs, the only factor affecting the accuracy of species classification was the use of the augmented dataset. However, in the analysis based on the whole epochs, four factors such as the use of the Adam optimizer, the earlywood part dataset, the whole part dataset, and the SGD optimizer were confirmed to affect to species classification. In Chapter 4, the classification performance and factors affecting species classification performance using a dataset of cross-sections of the bark of the seven Quercus species and a CNN architecture were examined. The accuracy and loss were stabilized at approximately 15 to 20 and 70 to 80 epochs for the augmented and non-augmented condition, respectively. In the final five epochs, the RMSProp-augmented condition achieved the highest accuracy of 89.8%, whereas the Adam-augmented condition achieved the lowest accuracy of 73.8%. Regarding the loss, SGD-non-augmented condition was the lowest at 0.498, whereas Adam-augmented condition was the highest at 2.740. The highest accuracy was influenced by RMSProp at 0.194. Dataset augmentation had a significant influence on accuracy at 0.456. Homogeneous subsets among the validation conditions indicated that the accuracy and loss were classified into the same subset using an augmented dataset during the training, regardless of the optimizer. Only Adam and RMSProp with non-augmented datasets were categorized into the same subset during the test. Hence, species classification using CNN and sclereid characteristics in the bark was feasible, and RMSProp with augmented datasets showed optimal performance for species classification. Keywords: species classification, Convolutonal Neural Networks (CNNs), commercial softwood, Oak, Quercus, Bark
더보기서지정보 내보내기(Export)
닫기소장기관 정보
닫기권호소장정보
닫기오류접수
닫기오류 접수 확인
닫기음성서비스 신청
닫기음성서비스 신청 확인
닫기이용약관
닫기학술연구정보서비스 이용약관 (2017년 1월 1일 ~ 현재 적용)
학술연구정보서비스(이하 RISS)는 정보주체의 자유와 권리 보호를 위해 「개인정보 보호법」 및 관계 법령이 정한 바를 준수하여, 적법하게 개인정보를 처리하고 안전하게 관리하고 있습니다. 이에 「개인정보 보호법」 제30조에 따라 정보주체에게 개인정보 처리에 관한 절차 및 기준을 안내하고, 이와 관련한 고충을 신속하고 원활하게 처리할 수 있도록 하기 위하여 다음과 같이 개인정보 처리방침을 수립·공개합니다.
주요 개인정보 처리 표시(라벨링)
목 차
3년
또는 회원탈퇴시까지5년
(「전자상거래 등에서의 소비자보호에 관한3년
(「전자상거래 등에서의 소비자보호에 관한2년
이상(개인정보보호위원회 : 개인정보의 안전성 확보조치 기준)개인정보파일의 명칭 | 운영근거 / 처리목적 | 개인정보파일에 기록되는 개인정보의 항목 | 보유기간 | |
---|---|---|---|---|
학술연구정보서비스 이용자 가입정보 파일 | 한국교육학술정보원법 | 필수 | ID, 비밀번호, 성명, 생년월일, 신분(직업구분), 이메일, 소속분야, 웹진메일 수신동의 여부 | 3년 또는 탈퇴시 |
선택 | 소속기관명, 소속도서관명, 학과/부서명, 학번/직원번호, 휴대전화, 주소 |
구분 | 담당자 | 연락처 |
---|---|---|
KERIS 개인정보 보호책임자 | 정보보호본부 김태우 | - 이메일 : lsy@keris.or.kr - 전화번호 : 053-714-0439 - 팩스번호 : 053-714-0195 |
KERIS 개인정보 보호담당자 | 개인정보보호부 이상엽 | |
RISS 개인정보 보호책임자 | 대학학술본부 장금연 | - 이메일 : giltizen@keris.or.kr - 전화번호 : 053-714-0149 - 팩스번호 : 053-714-0194 |
RISS 개인정보 보호담당자 | 학술진흥부 길원진 |
자동로그아웃 안내
닫기인증오류 안내
닫기귀하께서는 휴면계정 전환 후 1년동안 회원정보 수집 및 이용에 대한
재동의를 하지 않으신 관계로 개인정보가 삭제되었습니다.
(참조 : RISS 이용약관 및 개인정보처리방침)
신규회원으로 가입하여 이용 부탁 드리며, 추가 문의는 고객센터로 연락 바랍니다.
- 기존 아이디 재사용 불가
휴면계정 안내
RISS는 [표준개인정보 보호지침]에 따라 2년을 주기로 개인정보 수집·이용에 관하여 (재)동의를 받고 있으며, (재)동의를 하지 않을 경우, 휴면계정으로 전환됩니다.
(※ 휴면계정은 원문이용 및 복사/대출 서비스를 이용할 수 없습니다.)
휴면계정으로 전환된 후 1년간 회원정보 수집·이용에 대한 재동의를 하지 않을 경우, RISS에서 자동탈퇴 및 개인정보가 삭제처리 됩니다.
고객센터 1599-3122
ARS번호+1번(회원가입 및 정보수정)