Image text location method and device based on connective component and support vector machine

The invention discloses a text location method and a text location device in images based on connected components and support vector machine. The text location device comprises: an image segmentation unit; a connected region analysis unit; a unit for obtaining connected components characteristics and determining threshold value; a support vector machine classification unit; a unit for combining connected components into text region; and a unit for obtaining and determining text region statistical characteristics. The method comprises: dividing an input image to gain an image layered result; using connected components analysis to analyse prospect layer to gain a set of connected components; extracting the connected component characteristics, and using a structure of a cascade threshold classifier to exclude a plurality of non character connected components, and then using a support vector machine classification method to recognize if the rest candidate character connected components are character connected components; combining the rest connected components into candidate text regions according to principles that characteristics are consistent and distance is close, and extracting the characteristics of the candidate text regions, and using empirical threshold value to determine if the characteristics are the text regions.