E. Bayro-Corrochano and E. Hancock (Eds.): CIARP 2014, LNCS 8827, pp. 1014–1021, 2014.
© Springer International Publishing Switzerland 2014
Comparative Evaluation of Edge Linking Methods
Using Markov Chain and Regression Applied Heuristic
Haklin Kimm, Neda Abolhassani, and Eun-Joo Lee
Computer Science Department
East Stroudsburg University of Pennsylvania
East Stroudsburg, PA, USA
{hkimm,elee}@po-box.esu.edu
Abstract. There have been many studies on how to develop accurate edge
detection algorithms for various applications – especially processing geographic
images and maps, say coastline images. In this paper, we present edge linking
algorithms, based on a heuristic approach using regression analysis and Markov
chain technique respectively, for the coastline images. The heuristic approach
consists of costs that are based on the distance and direction of the edge
terminators while the Markov chain technique has been developed to
investigate possible line drawing options to reconnect the broken edges so that a
Markov transition matrix is generated in order to find the suitable edge
terminators that can be reconnected. In this paper both techniques of using
Markov chain and regression analysis have been developed and their outcomes
have been evaluated comparatively upon their accuracy of reconnecting the
broken edges.
Keywords: Edge detection and linking, Markov Chains, Regression based
heuristic, Image Processing, Coastline images.
1 Introduction
Edges are considered as one of the most significant features of an image. Many of the
edge detectors work based on the gradient at an edge point and the direction of the
edge on that point [1], [2]. Conventional edge detectors have some problems due to
differentiation functions and noises in an image. The source for the noise problem in
coastline detection of satellite images can be clouds or other objects that result in an
unclear image of the position of ocean and nearby land area [3], [4]. There have been
various edge detection algorithms such as Prewitt, Sobel, Canny and Morphological
that have been applied to the coastal satellite images [5]. In this paper, we present edge
linking algorithms based on a heuristic function using regression analysis and Markov
chain technique respectively. The heuristic approach, say function, consists of costs
which are based on the distance and direction of the edge terminators. The proposed
heuristic function is explained in detail with its regression analysis technique in later
section; and followed by Markov chain technique for reconnecting edges [6], [7].
Due to presence of non-continuous edges in the coastline images of edges, this
work first implements an edge linking method which is based on Markov transition