Method and apparatus for automatic recognition of image and text or graphics areas on printed masters

• US 4,504,972 A
• Filed: 01/26/1982
• Issued: 03/12/1985
• Est. Priority Date: 02/27/1981
• Status: Expired due to Fees

• Current Assignee: Siemens AG
• Original Assignee: Siemens AG
• Inventors: Scherl, Wolfgang, Fuchsberger, Hermann, Wahl, Friedrich M., Abele, Ludwig
• Primary Examiner(s): Boudreau, Leo H.
• Application Number:
  US06/342,898
• Time in Patent Office: 1,141 Days
• Field of Search: 382/18, 382/51, 382/9, 358/282
• US Class Current: 382/171
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

A method and apparatus for automatically recognizing the presence of an image area and a text or graphics area on a printed master which is being examined for determination of the textual content thereof employ an optoelectronic video scanner, the scanned values obtained therefrom being digitized and stored in a memory. The input master is schematically divided into small overlapping windows and a number of length of run histograms are generated by a computer for each such window. The particular characteristics of each of the histograms are examined for determination as to whether the histograms correspond to a text or graphics area or an image area of printed material on the master.

Claims

1. A method for automatically recognizing and distinguishing between image areas and text or graphics areas a printed master comprising the steps of:

optoelectronically scanning said printed master and generating analog signals representing the information contained on said printed master;

assigning a first binary value to analog signals having a value above a preselected value and assigning a second binary value to analog signals falling below said preselected value;

storing said binary values in a data field in a memory;

dividing said data field into a grid consisting of a plurality of windows in said memory, said windows having edge lengths which are not less than the spacing between two lines of text on said printed master;

generating four different length of run histograms for each said window; and

analyzing said length of run histograms for deriving values therefrom for determining whether the window associated therewith represents a text or graphics area or an image area of said printed master.

2. The method of claim 1 wherein said preselected value is a digital threshold value.

3. The method of claim 1 wherein said windows in said grid partially overlap.

4. The method of claim 1 wherein the step of generating four different length of run histograms for each said window is further defined by generating a length of run histogram for horizontal black areas (RL_h,s) and generating a length of run histogram for vertical black areas of said printed master (RL_v,s) and wherein the step of analyzing said length of run histograms is further defined by generating an evaluation value S according to the equation:

##EQU3## wherein S_H is a selected value, l is the length of run for said histograms.

5. The method of claim 4 wherein said step of generating four different length of run histograms is further defined by generating a length of run histogram for horizontal white areas of said printed master (RL_h,w) and generating a length of run histogram for vertical white areas of said printed master (RL_v,w) and wherein said step of analyzing said length of run histograms is further defined by generating an evaluation value RLD according to the following equation:

##EQU4##

6. The method of claim 5 wherein the step of analyzing said length of run histograms is further defined by checking whether the value in the length of run histogram for horizontal white areas for the longest horizontal white length of run (l_max) is unequal to 0.

7. The method of claim 6 wherein S_H is equal to 10 and wherein said step of analyzing said length of run histograms is further defined by determining whether the condition:

space="preserve" listing-type="equation">(S>

2.0·

10.sup.-2) (RLD>

12) (RL.sub.h,w (l.sub.max)≠

0)

exists, whereby a text area of said printed master is present if said condition is satisfied.

8. An apparatus for automatically recognizing text or graphics areas and image areas on a printed master comprising:

a means for optoelectronically scanning said printed master for generating analog signals corresponding to the information carried thereon;

a means for converting said analog signals into binary signals;

a memory for storing said binary signals in a data field, said memory having a grid having a plurality of windows therein superimposed on said data field;

a means for generating four different length of run histograms from the binary signals contained in each said window in said memory; and

a means for analyzing said length of run histograms and generating evaluation values associated therewith, said evaluation values determining whether a text or graphics area or an image area is present in the window associated with said length of run histograms.