SYSTEM FOR DISCRIMINATING DOCUMENT ORIENTATION

Document image data entered from a scanner are separated into a plurality of areas by an area separation unit. Attributes are assigned to respective ones of the plurality of partial areas obtained in the area separation unit. For instance, a character area in the main body of text and a character area in a table are examples of area attributes. Each of these attributes is assigned a degree of priority in advance. A character recognition/orientation discrimination unit detects character orientation in each of the plurality of partial areas and discriminates document orientation. The orientation of the document image data is determined based upon the document orientation of each partial area discriminated by the character recognition/orientation discrimination unit and the degree of priority of the attribute assigned to each partial area. Further, first and second recognition units for recognizing characters used in the Japanese and English languages, respectively, are provided, and the image data undergo recognition by each of these recognition units. The recognition rate of each result of recognition is obtained, the recognition rates are judged by a decision unit and one of the results is selected by a selector based upon the judgment made. The selected result of recognition is outputted.