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
- 학위논문
- 저자정보
- 지도교수
- 김선종
- 발행연도
- 2014
- 저작권
- 부산대학교 논문은 저작권에 의해 보호받습니다.
이용수2
이 논문의 연구 히스토리 (2)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
We can often see the trees in the park or roadside, and you don''t know species of the tree. But, kindly name tag attached. Also In nature we don''t know the species of trees. Tree consists of leaves, flowers, bark and etc, and them species is determined by visual observation. In addition, the bark can be observed in spring, summer, fall and winter all of seasons. Also, damage due to changes in the growth process is small. Because of these benefits, the bark is suitable for classification. So, to improve the performance of the classifier system, effective classification system model is required. If you are interested in Landscape Trees proposed model will be a good reference. In this paper, using effective weighted model, improve the performance of trees classification. This model is simple and easy to implement and provides high performance.
Texture feature extraction methods, wavelet both GLCM is used. First of all, wavelet transform is applied to the input image. Next, the GLCM was applied to each area of the wavelet image. In addition, GLCM texture feature of showing high performance in the 6 kinds is used in the proposed model and the images used in the experiment were collected by the author of this paper. The results of experiments on 35 species, When using a single texture features showed 59%. On the other hand, When applying the proposed model, the performance of 88.57% was obtained.
In conclusion, better performance than the conventional methods show and easy-to-implement advantage. If you applied this method, the application may be obtained high performance.
Texture feature extraction methods, wavelet both GLCM is used. First of all, wavelet transform is applied to the input image. Next, the GLCM was applied to each area of the wavelet image. In addition, GLCM texture feature of showing high performance in the 6 kinds is used in the proposed model and the images used in the experiment were collected by the author of this paper. The results of experiments on 35 species, When using a single texture features showed 59%. On the other hand, When applying the proposed model, the performance of 88.57% was obtained.
In conclusion, better performance than the conventional methods show and easy-to-implement advantage. If you applied this method, the application may be obtained high performance.
목차
1. 서 론 52. 관련연구 72.1 웨이브릿 변환(DWT:Discrete Wavelet Transform) 72.2 GLCM(Gray Level Co-occurrence Matrix) 102.3 수피의 질감 추출 152.3.1 웨이브릿 에너지를 이용한 질감 추출 152.3.2 웨이브릿과 GLCM을 혼합한 질감 추출 172.3.3 웨이브릿의 최적 파라미터 추출 192.3.4 GLCM의 최적 파라미터 추출 232.3.5 성능 비교 253. 효과적인 수피 분류를 위한 질감의 가중치를 이용한 방법의 제안 284. 실험결과 및 고찰 335. 결 론 43참고문헌 44Abstract 47감사의 글 49
최근 본 자료
댓글(0)
0