應用小波神經網路於高光譜影像分類

Wavelet Networks for Hyperspectral Image Classification

楊琇涵(Hsiu-Han Yang)

指導教授 ： 徐百輝

國立臺灣大學/工學院/土木工程學研究所/碩士(2007年)

https://doi.org/10.6342/NTU.2007.00400

摘要

高光譜影像因具有高維度之特性而無法直接應用傳統的統計分類方法進行影像分類。為了解決此問題，可在分類之前先進行高光譜影像特徵萃取；另一種可行之解決方式則是採用類神經網路進行影像分類。為了提高神經網路處理高維度資料的分類效率，可利用小波轉換進行高光譜影像特徵萃取，再以倒傳遞神經網路方法進行分類，然而小波特徵萃取法中，所選定的的尺度與平移參數並無法完全反應各類別光譜曲線的特性。本文提出利用小波神經網路法直接對高光譜影像進行分類，此方法在網路的學習過程中，同時對網路的權值、小波轉換的尺度及平移參數進行最佳化，達到特徵萃取及分類的效果。實驗結果顯示，相較於傳統的主軸分析特徵萃取法以及小波特徵萃取法，以小波神經網路為基礎的高光譜影像分類器能獲得較佳的分類結果。

關鍵字

高光譜影像 ； 小波特徵萃取 ； 小波神經網路 ； 維度縮減 ； 影像分類

並列摘要

The idea of using artificial neural network has been proven useful for hyperspectral image classification. However, the high dimensionality of hyperspectral images usually leads to the failure of constructing an effective neural network classifier. To improve the performance of neural network classifier, wavelet-based feature extraction algorithms can be applied to extract useful features for hyperspectral image classification. However, the extracted features with fixed position and dilation parameters of the wavelets provide insufficient characteristics of spectrum. In this study, wavelet networks which integrates the advantages of wavelet-based feature extraction and neural networks classification is proposed for hyperspectral image classification. Wavelet networks is a kind of feed-forward neural networks using wavelets as activation function. Both the position and the dilation parameters of the wavelets are optimized as well as the weights of the network during the training phase. The value of wavelet networks lies in their capabilities of optimizing network weights and extracting essential features simultaneously for hyperspectral images classification. The experiment results showed that the wavelet networks classifier has better classification accuracy than traditional back propagation neural networks with features from wavelet transform and from principle component analysis, and exactly is an effective tool for classification of hyperspectral images.

並列關鍵字

Hyperspecteal Images ； Wavelet-based Feature Extraction ； Wavelet Networks ； Dimensionality Reduction ； Image Classification

參考文獻

Hsu, P.-H. (2003). "Spectral Feature Extraction of Hyperspectral Images using Wavelet Transform," National Cheng Kung University, Tainan, Taiwan, R.O.C.

Angrisani, L., Daponte, P., and D'Apuzzo, M. (2001). "Wavelet network-based detection and classification of transients." IEEE Transactions on Instrumentation and Measurement,, 50(5), 1425-1435.

Bellman, R. E. (1961). Adaptive control processing : a guided tour, Princeton University Press.

Benediktsson, J. A., Sveinsson, J. R., and Amason, K. (1995). "Classification and feature extraction of AVIRIS data." IEEE Transactions on Geoscience and Remote Sensing, 1194-1205.

Bishop, C. M. (1995). Neural Networks for Pattern Recognition Oxford University Press, New York.