A System to Retrieve Text / Symbols from Color Maps using Connected Component and Skeleton Analysis

Automatic separation of Text and Graphic Symbols in document images is one of the fundamental aims in Graphics Recognition. In Maps, separation of Text and Graphic Symbols involves many challenges because the text and symbol frequently touches/overlaps to the long lines of street, river, border of the regions etc. of the maps with similar color. Sometimes the colors in a simple character are gradually distributed which adds extra difficulty in the problem. In this paper we proposed a system to retrieve text/symbols from maps. Here, at first, we separate the maps into different layers according to color features and then connected component features and skeleton information are used to identify text characters, symbols from graphics on the basis of their geometrical features. From the experiment we obtained encouraging results.