Method and apparatus for producing a hybrid data structure for displaying a raster image

• US 5,625,711 A
• Filed: 08/31/1994
• Issued: 04/29/1997
• Est. Priority Date: 08/31/1994
• Status: Expired due to Term

• Current Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Nicholson, Dennis G., King, James C.
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): Tadayon, Bijan
• Application Number:
  US08/298,655
• Time in Patent Office: 972 Days
• Field of Search: 382/176, 382/177, 382/180, 382/179, 382/101, 382/102, 382/112, 382/113, 382/138, 382/155, 382/159, 382/165, 382/169, 382/170, 382/171, 382/172, 382/173, 382/175, 382/178 , 382/181, 382/182, 382/185, 382/187, 382/186, 382/190, 382/209, 382/217, 382/224, 382/228, 382/229, 382/230, 382/231, 382/232, 382/282, 382/284, 382/309, 395/147, 395/148, 395/144, 358/452, 358/453, 358/530, 358/537, 358/538, 358/539, 358/540
• US Class Current: 382/224
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/127 with the intervention of an operator
• CPC Class Codes: G06V 30/268 Lexical context
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition
• CPC Class Codes: H04N 1/4115 involving the recognition of specific patterns, e.g. by symbol matching

Abstract

A system for producing a raster image derived from coded and non-coded portions of a hybrid data structure from an input bitmap including (1) a data processing apparatus, (2) a recognizer which performs recognition on an input bitmap to the data processing apparatus to detect identifiable objects within the input bitmap, (3) a mechanism for producing a hybrid data structure including coded data corresponding to the identifiable objects and non-coded data derived from portions of the input bitmap which do not correspond to the identifiable objects, and (4) an output device capable of developing a visually perceptible raster image derived from the hybrid data structure. The raster image includes raster images of the identifiable objects and raster images derived from portions of the input bitmap that do not correspond to the identifiable objects. The invention includes a method for producing a hybrid data structure for a bitmap of an image having the steps of: (1) inputting a signal comprising a bitmap into a digital processing apparatus, (2) partitioning the bitmap into a hierarchy of lexical units, (3) assigning labels to a label list for each lexical unit of a predetermined hierarchical level, where labels in the label list have an associated confidence level, and (4) storing each lexical unit in a hybrid data structure as either an identifiable object or a non-identifiable object.

Claims

1. A system for producing a raster image derived from a hybrid data structure including coded and non-coded portions from an input bitmap, the system comprising:

(a) a data processing apparatus;

(b) means for performing recognition on an input bitmap that has been entered into said data processing apparatus to detect identifiable objects within said input bitmap, said means for performing recognition including;

(i) means for comparing each of said identifiable objects with a portion of said input bitmap corresponding to said identifiable object; and

(ii) means for adjusting the size of said identifiable object if said identifiable object is within a threshold size of said corresponding input bitmap portion;

(c) means for creating a hybrid data structure including coded portions corresponding to said identifiable objects and non-coded portions derived from portions of said input bitmap which do not correspond to said identifiable objects; and

(d) an output device for developing a visually perceptible raster image from said hybrid data structure that includes coded images of said identifiable objects and non-coded images of said non-identifiable portions of said input bitmap.

2. A system as recited in claim 1 wherein said means for creating a hybrid data structure stores scale factors in said hybrid data structure, said scale factors being used to display said identifiable objects at said adjusted size.

3. A method for producing a hybrid data structure from a bitmap of an image including identifiable objects and non-identifiable objects comprising the steps of:

inputting a signal comprising a bitmap of an image into a digital processing apparatus;

determining on said digital processing apparatus a geometric correction of said bitmap, said determining a geometric correction step including creating a distortion map of said bitmap and creating a layout correction transform from said distortion map and said bitmap;

partitioning on said digital processing apparatus said bitmap into lexical units;

assigning on said digital processing apparatus at least one label and an associated confidence level to each lexical unit; and

storing on said digital processing apparatus each lexical unit in a hybrid data structure as an identifiable object if a label for said lexical unit has a confidence level greater than a threshold confidence level, and as a non-identifiable object if no label for said lexical unit has a confidence level greater than said threshold confidence level.

4. A method for producing a hybrid image comprising:

inputting a bitmap representing an image into a digital processing apparatus;

segmenting said bitmap into lexical units;

assigning a typeface to each of said lexical units of said bitmap;

recognizing on said digital processing apparatus identifiable objects in said bitmap;

performing a size adjustment to said identifiable objects; and

creating with an output device coupled to said digital processing apparatus a visually perceptible image comprising rendered images of said size-adjusted identifiable objects and bitmap images of objects that were not recognized.

5. A method for producing a hybrid data structure from a bitmap of an image including identifiable objects and non-identifiable objects comprising the steps of:

inputting a signal comprising a bitmap of an image into a digital processing apparatus;

partitioning on said digital processing apparatus said bitmap into lexical units, wherein said lexical units are organized into levels of a hierarchy which include a blob level, a character level, a word level, a text line level, a text block level, a page level, and a document level;

assigning on said digital processing apparatus at least one label and an associated confidence level to each lexical unit; and

storing on said digital processing apparatus each lexical unit in a hybrid data structure as an identifiable object if a label for said lexical unit has a confidence level greater than a threshold confidence level, and as a non-identifiable object if no label for said lexical unit has a confidence level greater than said threshold confidence level.