查詢結果分析
相關文獻
- Classification of Multi-Spectral Image Data Considering Non-Gaussian Distribution and Inter-Pixel Class Dependency
- Approximated Clustering via Grey Mountain Clustering Method
- 模糊統計分類在臺灣地區失業率分析與預測之應用
- 「佛教圖書分類法1996年版」分類釋疑
- 臺灣資料地理複分探究
- 關於圖書分類法的修訂
- REAL/WHO淋巴瘤的分類
- 海峽兩岸「中圖法」之比較
- 「佛教圖書分類法1996年版」分類釋疑
- 以最小錯誤分類法統計震災地區土壤抗液化強度與SPT 調查結果之關係
頁籤選單縮合
題 名 | Classification of Multi-Spectral Image Data Considering Non-Gaussian Distribution and Inter-Pixel Class Dependency=用相鄰像素類別相關性增強多頻帶影像之分類正確性 |
---|---|
作 者 | 蘇怡仁; 林巍聳; | 書刊名 | Journal of the Chinese Institute of Electrical Engineering |
卷 期 | 5:4 1998.11[民87.11] |
頁 次 | 頁287-295 |
分類號 | 448.6 |
關鍵詞 | 多頻帶影像; 分類法; 類別相關性; 非參數化估測法; Spectral image; Classification; Inter-pixel class dependency; |
語 文 | 英文(English) |
中文摘要 | 本文提出用相鄰像素的類別相關性輔助頻譜特徵,增強多頻帶影像分類的正確性, 因而發展出頻譜特徵附加相臨像素之間類別相關性的分類法,這個新分類法先利用非參數化 方法估測各類別的頻譜分佈,然後根據頻譜特徵分類,不能順利確認類別者,再衡量相臨像 素的類別相關性于以分類,如此,空間相關性的資訊只用於處理難以按頻譜特徵辨認及分類 的像素,而非所有的像素,因而可以節省處理的時間,並同時達到增加分類正確性的目的。 實例中,用此新分類法與高氏最相似分類法、逆傳類神經網分類法相比較,證實這個新分類 法確實有效。 |
英文摘要 | Classification can partition the feature space of a multi-spectral image into separated regions corresponding to specified classes. Pixels close to one or some of the training examples can be classified easily. Else piixels may be either different from the examples or near the class boundary, and classification by simply evaluating spectral characteristics can be far from accurate or even impossible. By considering inter-pixel class dependency as auxiliary information in spectral classification, this paper proposes a new classifier to improve the accuracy in classifying multi-spectral image data. This new classifier evaluates the spectral characteristics of each pixel first to categorize it as a classifiable or a spectrally uncertain pixel. Inter-pixel class dependency is then added to classify the uncertain pixels. The class similarity between spatially adjacent pixels of remotely observed multii-spectral image motivates the method of using inter-pixel class dependency. A spatial filter with pre-specified parameters is used to describe the dependency. The distributions of the probability density functions for classification are not assumed to be normal and a non-parametric method is adopted to estimate the class-conditional probabilities. Comparison with those using Gaussian maximum likelihood and back-propagation neural networks is demonstrated and excellent simulation results are obtained. |
本系統中英文摘要資訊取自各篇刊載內容。