數位影像的使用越來越普及，不再像是以往一樣只有文字資訊，各種數位影像的相關技術顯得更重要，像是影像切割，影像壓縮，影像搜尋等等。數位影像分割技術便是在本論文中要討論的。
本論文提出兩種影像種類的影像切割，一類是文件影像切割，另一種是圖片影像切割。文件影像切割的目的是將影像中文字與圖片的部分區分判斷出來，希望將文字與影像區分出來之後，能將文字的部分拿來作應用，像是文字辨識之類。圖片影像的切割則是根據不的需求有不同的切割方式，使用不同的特徵表示方式來當成影像切割的依據，可以利用影像的顏色特徵，紋路特徵或是轉換特徵空間之後來作影像切割。本論文利用以上的特徵和一些特徵轉換，或是其他的特徵表示表示法，有各種不同的影像切割方式。最後，在本論文中提出這些影像切割技術的實作上的比較。

Image segmentation sees in many applications such as image database retrieval, document processing, optical character recognition, and etc. A good segmentation results in better performance of applications. In this thesis, several image segmentation techniques are studied. They are edge based, texture based, knowledge based and color based techniques. We successfully implement the algorithms and test their feasibility. The algorithms are applied to both nature images and document images and their performance are compared. Finally, the computational complexities of these algorithms are compared. The advantages and disadvantages of them are discussed.

[1]Chen Wei-Yuan and Chen Shu-Yuan,
“Adaptive Page Segmentation for Color Document
　　Images”, Proc. of IPPR Conference on Computer
　　Vision, Graphics and Image Processing, Taiwan,
　　R.O.C., pp.421-429.

[2]Chen Yixin and Wang James Z. ,
“A Region-Based Fuzzy Feature Matching Approach
　　 to Content-based Image Retrieval “, IEEE
　　 Trans on PAAMI , vol.24 , No.9 , p1252-1267 ,
　　 Sep 2002.

[3]Duda R. O. and Hart P. E.,
“Pattern Classification and Scene Analysis”,
　　 New York : Wiley, 1973.

[4]Gose Earl, Johnsonbaugh Richard and Jost Steve,
“Pattern Recognition and Image Analysis”,
　　Prentice Hall, 1996.

[5]Gonzalez Rafael C. , Woods Richard R. ,
“Digital Image Processing” ,( Second Edition
　　), Prentice Hall , international edition , P136
　　, P138 , 2002.

[6]Haykin Simon S. ,“Neural Networks: A
　　Comprehensive Foundation“ ,( 2nd Edition ),
　　Prentice Hall , international edition ,1999.

[7]Jain A. K. and Dubes R. C.,”Algorithms and
　　Clustering Data”, Engle-wood Cliffs, NJ :
　　Prentice-Hall, 1988.

[8]Manjunath B.S. and Ma W.Y. , ”Texture Features
　　for Browsing and Retrieval of Image Data” ,
　　IEEE Trans on PAAMI , vol.18 , No.8 , p837-842
　　, Aug 1996 .

[9]Ma W.Y. and Manjunth B.S. ,” Edge Flow : A
　　Framework of Boundary Detection and Image
　　Segmentation “, IEEE int. conf. on Computer
　　Vision and Pattern Recognition , 1997.

[10]Ma Wei-Ying and Manjunath B.S. , “Edge Flow :
　　 A Technique for Boundary Detection and Image
　　 Segmentation”. IEEE Trans. on Image
　　 Processing , Vol 9 , No.8 , August 2000.

[11]Malladi Ravikanth , Sethian James A. , and
　　 Vemuri Baba C. , “Shape Modeling with Front
　　 Propagation: A Level Set Approach .”,IEEE
　　 Transactions on pattern analysis and machine
　　 intelligence , Vol. 17 , No.2 , February 1995.

[12]Su Mu-Chun and Chou Chien-Hsing, ” A Modified
　　 Version of the K-Means Algorithm with a
　　 Distance Based on Cluster Symmetry”, IEEE
　　 trans. on pattern analysis and machine
　　 intelligence. Vol.23, No.6, June 2001.

[13]Sumengen Baris , Manjunth B.S. ,and Charles
　　 Kenney , “Image Segmentation using Curve
　　 Evolution” , Asilomar Conference on Signals
　　 Systems , Systems and Computers , Monterey ,
　　 CA,November 2001.

[14]Suen Hong-Ming and Wang Jhing-Fa , “Uniform-
　　 and Nonuniform-Colored Text String Extraction
　　 for Color Document Images.”,1996
　　 international computer Symposium (ICS’96) om
　　 image Processing and Character Recognition ,
　　 pp.161-166 , 1996.

[15]Xu Chenyang , Prince Jerry L.
　　 ,”Snakes,Shapes,and Gradient Vector
　　 Flow”,IEEE Transactions On Image Processing ,
　　 Vol 7 , No.3 , March 1998.