In fact, in ABBYY's OCR editor, the recognition degree of the table can reach 100% by adjusting the recognition of the table area. I use an actual case to illustrate how to adjust an unrecognizable table.
First, use ABBYY FineReader PDF 15 software to open a PDF file generated by scanning a paper form. Because the clarity of paper forms is not high, the scanned PDF file is not very effective, which will make ABBYY's OCR editor identify errors, which is a common problem in practical use.
Click the Identify button and select Identify and Verify in OCR Editor.
After the recognition is completed, in the OCR editor interface, look at the copy file on the right and find that the table is not fully recognized. For example, a vertical bar is missing from the left side of the registration number; "Unregistered students ……" is missing the left and right vertical lines, and the table in the "Signature" section below is unrecognizable. At this time, please note that "Accurate to Copy" must be selected as the Save Format.
On the left source file, delete the text box in the table, click "Make Table Area" on the toolbar, and set a new drawing table area for the table by adjusting the add table area. In the process of setting, attention should be paid to the alignment of vertical lines and the overlapping of horizontal lines to avoid the problems of dislocation and inconsistent thickness of the identified table borders.
After redrawing the table area on the source file, click "Identify Page" to re-identify the source file. After the appraisal, check the form again and find that the copy is consistent with the original.
Then click the "Verify" button to modify the content where the error was found. After error correction, the whole process of source file identification is completed.
Finally, the recognized file is saved as a Word document, and the scanned form is converted into an electronic file in Word format.
abstract
Due to the clarity and scanning accuracy of the original paper document, the contents in the PDF file will be blurred, so that the OCR text recognition software of ABYY Finereader PDF15 software can not fully recognize the lines of the table, which leads to the deletion of the table. However, after redrawing the table area, a complete table can be obtained by identifying the basis again.