λ-Connectedness and Its Applications

This paper attempts to provide a systematic view to the λ-connectedness method. This method is for classification/segmentation, fitting/reconstruction, and inference. A common type of partial connectivity that describes the phenomenal of gradual variation is studied in various domains. The previous research work on λ-connectedness was abstracted and integrated into a unified framework: a networkor graph-based system. This method focuses on a way to solve a set of problems that λ-connectedness can apply to rather than to give a solution to a particular problem. This technique is based on a graph G = (V, E) and an associate function ρ on the vertices of the graph, where ρ is called the potential function. A measure Cρ(x, y) is defined for the λconnectedness on the vertices x, y ∈ G with respect to ρ. For a certain λ ∈ [0, 1], x and y are said to be λ-connected if Cρ(x, y) ≥ λ. So, λ-connectedness is a type of fuzzy relation. If every pair of vertices are λ-connected, then ρ is λ-connected on G. Therefore, λ-connectedness is also a measure of continuity in discrete spaces and systems. Based on this concept, the relationship between graph theory and λ-connectedness is discussed, and the λ-connected segmentation and fitting are introduced. Further more, the fast graph-theoretic algorithms to problems of λ-connectedness are described. At the end, the relationship among λ-connectedness, rough sets, belief networks, and network economics and resource management are also investigated. The λ-connectedness method can be viewed as a special application of graph theory, a fuzzy system method, or a systematic method for problems in uncertainty.

[1]  Robert M. Haralick,et al.  Automatic multithreshold selection , 1984, Comput. Vis. Graph. Image Process..

[2]  Azriel Rosenfeld,et al.  'Continuous' functions on digital pictures , 1986, Pattern Recognit. Lett..

[3]  R. Kohler.  A segmentation system based on thresholding , 1981 .

[4]  L.-C. Tsai,et al.  Ionogram analysis using fuzzy segmentation and connectedness techniques , 2000 .

[5]  Li Chen,et al.  Application of a fuzzy object search technique to geophysical data processing , 1994, Electronic Imaging.

[6]  Ching Y. Suen,et al.  A recursive thresholding technique for image segmentation , 1998, IEEE Trans. Image Process..

[7]  Zdzisław Pawlak.  Rough sets, rough functions and rough calculus , 1999 .

[8]  T. Pavlidis.  Algorithms for Graphics and Image Processing , 1981, Springer Berlin Heidelberg.

[9]  Li Chen.  λ-Measure for Bone Density Connectivity , 2006, 2006 IEEE International Symposium on Industrial Electronics.

[10]  Solomon Lefschetz,et al.  Introduction to Topology , 1950 .

[11]  Kevin Murphy,et al.  A brief introduction to graphical models and bayesian networks , 1998 .

[12]  Andrew K. C. Wong,et al.  A new method for gray-level picture thresholding using the entropy of the histogram , 1985, Comput. Vis. Graph. Image Process..

[13]  Li Chen,et al.  Gradually varied surface and its optimal uniform approximation , 1994, Electronic Imaging.

[14]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[15]  D.M. Mount,et al.  An Efficient k-Means Clustering Algorithm: Analysis and Implementation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  W. Marsden.  I and J , 2012 .

[17]  Lakhmi C. Jain,et al.  Introduction to Bayesian Networks , 2008 .

[18]  陈溧.  THE NECESSARY AND SUFFICIENT CONDITION AND THE EFFICIENT ALGORITHMS FOR GRADUALLY VARIED FILL , 1990 .

[19]  S. Soltani,et al.  SURVEY A Survey of Thresholding Techniques , 1988 .

[20]  A. Rosenfeld.  The fuzzy geometry of image subsets , 1984, Pattern Recognit. Lett..

[21]  Ronald W. Schafer,et al.  Multilevel thresholding using edge matching , 1988, Comput. Vis. Graph. Image Process..

[22]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[23]  Li Chen.  Λ-connectedness and Its Application to Image Segmentation, Recognition and Reconstruction , 2001 .