崩塌地的自動判釋方法裡，最常採用的方法為監督式分類法、非監督式分類法、或加入植生變遷與坡度因子來分析。但監督或非監督式其對雜訊與非崩塌地上誤判的現象仍需要改進；而植生變遷需多張影像判釋；坡度因子又需取決DTM來源與時效上的限制，本研究嘗試解決這些問題，且設計一套有效的判釋架構。
　　紋理可直接將影像中物件特徵作描述，且小波轉換具有良好的空間-頻率的局部分析與多層解析力分離特質，於是採用小波紋理特徵更能以少量的特徵值來表現出其紋理特性，於是本研究決定採用小波紋理特徵值進行影像判釋之作業。
　　本研究處理流程分二階段進行，第一階段，先設計一小波紋理特徵值為判定門檻，作為決定是否為涵蓋崩塌地之影像；第二階段，運用小波多層解析力分析將符合條件之影像分類為崩塌地與非崩塌地，最後將分類成果進行精度評估。此研究中使用50張大小一致、解析力相同的影像進行判釋作業，成果顯示整體精度為72.74﹪。
　　此判釋流程，在不同資料來源下仍可達到預期的效果，且減少了需要輔助資料所引起時效上的缺失，也降低了人為因素的干擾，雖判釋結果尚未能完全取代人工判釋，但仍提供了一個自動化且迅速的判釋模式，有助於大量批次化自動影像判釋之用。最重要地，相較於現今的自動判釋流程，此研究流程以較少時間、人為因素達到更好的精確度。

　　In the automatic identification approaches for landslides, the most common methods are supervised classification, unsupervised classification, or analyze the vegetation change with slop. However, supervised or unsupervised classifications methods need to improve the noises and mis-identification of non-landslides using vegetation change or such purpose require numbers of images and the slope information is limited by the source of DTM and also the effectiveness. Thus the reason, to design an effective structure of identification in solving these problems was carried out in this study.
　　Textures can describe the character of objects in the image directly, and wavelet transform possess the capability in partial analysis of space-frequency and also the feature of multiple resolutions. Using wavelet transform can display the texture features with a few characteristic values, this also why this research using wavelet texture values to perform the image identifications.
　　The procedure of this research separed into two stages. First, to design a feature value of wavelet texture as threshold in determining the images whether contain landslides. Second, applying wavelet multiple resolutions function to classify the images into regions of landslides and non-landslides. And the accuracy of the in classification was evaluated. There are 50 images with the same size and resolution was proceed in identification procedure. Such task the overall accuracy for 72.74﹪with wavelet transform.
　　This procedure can still achieve the expected goal with various images,and reduce the need for the auxiliaring information that is extra time required.By doing such,human interfering and error then can be avoid. Although the automatic identification results can not substitute the artificial identification completely. It provides an automatic and rapid identification schema with reasonable result that can identifying mamy images gathered with different plateform automatically.Most of all,the process result achive better accuracy with less time and human interact than the existing procedures

江良印，紋理特徵應用於遙測影像判釋之理論研究，國立台灣大學農業工程學系研究所碩士論文，70頁，1998。
李森吉，使用衛星影像作山區中大規模崩塌地之辨識，國立成功大學資源工程系碩士論文，104頁，1992。
吳佐川，臺灣地區崩塌地區域特性之研究，國立台灣大學森林研究所碩士論文，115頁，1993。
紀凱屏，影像雜訊過濾方法與效果之探討，國立成功大學測量工程研究所碩士論文，1990。
胡昌華、張軍波、夏軍、張偉，基於MATLAB的系統分析與設計—小波分析，西安電子科技大學出版社，1999.12。
唐德誠，灰度共現矩陣於多波段多極化SAR影像分類之研究，國防大學中正理工學院軍事工程研究所，2002 。
黃筱梅，SPOT衛星影像於裸露地變遷之偵測研究—以和社地區為例，國立臺灣大學森林學研究所碩士論文，82頁，2001。
曾建昌，使用小波係數具抗旋轉性之顏色紋理影像檢索系統，國立成功大學電機工程研究所碩士論文，1992。
陳駿賢，遙測及景觀分析技術於崩塌地判釋與變化之研究，私立逢甲大學土地管理研究所，2003。
張毓晉，影像分割，科學出版社，2001。
彭玉華，小波變換與工程應用，北京科學出版社，1999。
鄭文哲、蕭國鑫等，高屏溪上游土地利用及崩塌地調查計畫書，工研院能資所地239號報告，1990
劉守恆，衛星影像於崩塌地自動分類組合之研究，國立成功大學地球科學研究所碩士論文，2002。
劉進金，山崩之遙測影像自動分析，遙感探測第八期，頁60-90，1987。
劉進金、張寶堂，大型山崩之遙測辨認，遙感探測第十四期，頁41-68，1991。
廖軒吾，集集地震誘發之山崩，國立中央大學應用地質研究所碩士論文，90頁，2000。
戴德潤，利用SPOT衛星影像作中橫公路沿線附近大規模崩塌地辨認方法之初步研究，國立成功大學資源工程系碩士論文，95頁，1990。
蕭國鑫、尹承遠、劉進金、游明芳、王晉倫，SPOT影像與航照資料應用於崩塌地判識之探討，航測及遙測學刊，第八卷，第四期，29-42頁。
A.Laine, J. Fan, Texture classication by wavelet packet signatures,IEEE Trans., Pattern Anal. Mach. Intell. 15 (11),1186–1191,1993.
C.K. Chui, An introduction to wavelets, Academic Press,Boston, 1992.
Connors, R.W., and Harlow, C.A., Toward a Structural Textual Analyzer Based on Statistical Methods, in Rosenfeld, A(ed), Image Modeling, Academic, New York, pp.29-61, 1981.
Chang, T., Jay Kuo, C.C. ,Texture analysis and classification with tree-structured wavelet transform, IEEE Trans., Image Process2 (4), 429–440 , 1993.
Guangyi Chen, Tien D. Bui, Invariant Fourier-wavelet descriptor for pattern recognition, Pattern Recognition 32 ,1083-1088,1999.
Haralick, R. M., K. Shanmugam and I. Dinstein. Textural features for image classification , IEEE Trans., SMC: 610-621,1973.
I. Daubechies, The wavelet transform time–frequency localization and signal analysis, IEEE Trans. , Inf. Theory 36, 961–1005,1990.
J.M. Keller, S. Chen, R.M. Crownover, Texture description and segmentation through fractal geometry, Comput.Vision Graphical Image Process 45, 150–166,1989.
Jun Li, A Wavelet Approach to Edge Detection, Master of Science (Mathematics), Sam Houston State University. Huntsville, Texas.,2003
Lindsay, R.W., D.B.Percival, and D.A.Rothrock, The discrete wavelet transform and the scale analysis of surface properties of sea ice,IEEE Trans,Geosci.Remote Sens. 34,771-787,1996.
Mallat, S.,A theory of multiresolution signal decomposition:the wavelet representation,IEEE Trans.,Pattern Anal Machine Intell. 11, 674-693 , 1989a.
Mallat, S., Multiresolution Approximations and Wavelet Orthonormal bases of, Trans. Amer. Math. Soc., Vol. 315, 69-87, 1989b.
O.D. Faugeras, W.K. Pratt, Decorrelation methods of texture feature extraction, IEEE Trans, Pattern Anal. Mach. Intell. 2 ,323-332,1980.
Pun, C.-M.; Lee, M.-C.,Rotation-invariant texture classification usinga two-stage wavelet packet feature approach ,Vision, Image and SignalProcessing, IEE Proceedings,Volume148 Issue 6 ,422 -428 , Dec. 2001.
Raghuveer M. Rao and Ajit S. Bopardikar, Wavelet Transforms : Introduction to Theory and Applications, Addison Wesley Longman, ISBN 0-201-63463-5, 1998.
S. Arivazhagan , L. Ganesan ,Texture classification using wavelet transform,Pattern Recognition Letters 24,1513–1521,2003.
T. Chang and C. C. J. Kuo, Texture analysis and classification with tree-structured wavelet transform,IEEE Trans,Image Processing vol.2, 429-441, Oct. 1993.
T. Randen, J.H. HusHy, Multichannel ltering for image texture segmentation, Opt. Eng. 33 (8) ,2617–2625,1994.
T. Randen, J.H. HusHy, Filtering for texture classifaction: a comparative study, IEEE Trans, Pattern Anal. Mach. Intell.21 (4) ,291–310,1999.
Tang, Y.Y., Yang, L.H., Liu, J., and Ma, H.,Wavelet Theory and Its Application to Pattern Recognition,World Scientific,ISBN 981-02-3819-3, 2000.
Van de Wouwer, G., Schenders, P., Van Dyek, D,Statistical texture characterization from discrete wavelet representation ,IEEE Trans., Image Process. 8 (4), 592–598, 1999.
Zhou, J., D. L. Civco and J.A. Silander, A wavelet transform method to merge Landsat TM and SPOT panchromatic data, Int. J. Remote Sensing, 19(4), 743-757, 1998.
Zhu, C. and X. Yang, Study of remote sensing image texture analysis and classification using wavelet, Int. J. Remote Sensing, 19(16), 3197-3203, 1998.