Apparatus for extracting a text region in a document image

摘要: A peripheral distribution of filled pixels in a document image is calculated by projecting the an X-axis or Y-axis direction. Minima (TX1, ..., TY1, ...) are detected. The divided into plurality primary regions accordance with dividing lines (LV1, LH1, (Fig 5) intersecting minima direction and density each region assessed so that can be classified text (T), drawing (U) picture (V) 7). Thus, extracted automatically from without requiring specific manual operation for extracting operator.