Legend based elevation layers extraction from a color-coded relief scanned map

Published 1 January 2005

Clara Rus, Jaakko Astola

DOI10.1109/icip.2005.1530035

Citations1

TL;DR

This paper presents an approach to extract the elevation layers from a color-coded relief scanned map having as an input information the colors provided by the map's legend, working in the CIE L*u*v* color space.

Abstract

This paper presents an approach to extract the elevation layers from a color-coded relief scanned map having as an input information the colors provided by the map's legend. We work in the CIE L*u*v* color space. The mean shift filtering is used to reduce the printing details (the dithering effect). The colors are extracted from the legend by the randomised local search (RES) algorithm. The elevation layers are identified by computing the Euclidean distance between each color in the legend and each pixel in the scanned image and then using a threshold operation. Overlaps between the extracted layers are also considered in order to eliminate distortions.

Keywords

Computer Science

IEEE Transactions on Pattern Analysis and Machine IntelligenceMean shift: a robust approach toward feature space analysis

11,282 Citations2002Dorin Comaniciu, Peter Meer

It is proved the convergence of a recursive mean shift procedure to the nearest stationary point of the underlying density function and, thus, its utility in detecting the modes of the density.

Pattern RecognitionColor image segmentation: advances and prospects

1,686 Citations2001Heng-Da Cheng, X.H. Jiang +2 more

This survey provides a summary of color image segmentation techniques available now based on monochrome segmentation approaches operating in different color spaces and some novel approaches such as fuzzy method and physics-based method are investigated.

Pattern Analysis and ApplicationsRandomised Local Search Algorithm for the Clustering Problem

109 Citations2000Pasi Fränti, Juha Kivijärvi

This work introduces a new randomised local search algorithm for the clustering problem that is easy to implement, sufficiently fast, and competitive with the best clustering methods.

Segmentation of Scanned Maps in Uniform Color Spaces.

7 Citations1994B. Lauterbach, W. Anheier

A new color segmentation algorithm is presented, which is based on the uniform CIE-L*u*v* color space and its u'v' color table, which produces very clean segmentation results with smooth borders in particular in case of color-mixed region outlines of scanned full-color map prints.

Gray scale processing of hydrographic maps

4 Citations1996Øivind Due Trier, Torfinn Taxt +1 more

Experimental results indicate that the computationally intensive deconvolution and topographic analysis does not improve system performance, but the same high performance is achieved by binary analysis, provided a high quality locally adaptive binary method is used.

Map automatic input based on NN and GAs

2 Citations2003G. Zihua, Oscar C. Au

A new color image segmentation algorithms based on color space transformation and vectorization algorithm based on GA are presented in detail.

Intelligent segmentation of color geo-images

2 Citations2004Serguei Levachkine, Miguel Torres-Ruiz +1 more

This work presents an approach to a segmentation of color cartographic images using a simultaneous segmentation-recognition-interpretation system when successfully segmented objects of interest are labeled by the system in the same gray-level values, but are different for each type of object.