Abstract: According to an embodiment of the invention, a method and apparatus for image segmentation are described. An embodiment of a method comprises inserting a state comprising a set of image segmentations into a queue, the queue being ordered by priority, the set of image segmentations having a priority representing a bound for a quality of the segmentations; extracting the state in the queue having the highest priority; if the extracted state is a terminal state, halting and outputting the extracted state as a solution; if the extracted state is not a terminal state refining the extracted state into a plurality of sets of segmentations, each of the plurality of sets having a priority, inserting the plurality of sets of segmentations into the queue, and iteratively repeating the extraction of the state in the queue having the highest priority.

Abstract: The system of the present invention has a reference character database, which stores a multiplicity of reference characters, and a feature extractor which extracts shape information for each input character. For each reference character, the database lists shape information and reference line measurements indicating how reference lines pass through it. For example, the reference line measurements can be percentages of a height of a bounding box which bounds each reference and/or input character.In some embodiments, the input characters are collected into a stroke buffer and in other embodiments, they are collected into a line buffer. In all embodiments, the reference line estimation is performed for a series of input characters, whether as a full line of characters or as a collection of strokes.