×

Spatial recognition and grouping of text and graphics

  • US 7,729,538 B2
  • Filed: 08/26/2004
  • Issued: 06/01/2010
  • Est. Priority Date: 08/26/2004
  • Status: Expired due to Fees
First Claim
Patent Images

1. A computer readable medium having stored thereon executable software comprising:

  • a component that receives input comprising at least one entity comprising one or more strokes, wherein strokes associated with the input are generated in a non-linear sequence in time; and

    a recognition component that utilizes a simultaneous segmentation and recognition process to recognize the at least one entity in the input, the recognition component recognizes the at least one entity based at least in part on a predetermined minimum threshold distance between convex hulls of respective strokes associated with the input, wherein strokes are associated with the at least one entity when distance between convex hulls of respective strokes is less than the predetermined minimum threshold distance, and a predetermined maximum number of strokes per entity, and further wherein the simultaneous segmentation and recognition process comprises;

    linking strokes of the input in a graph to form connected subgraphs;

    applying a search method over the connected subgraphs of a proximity graph to determine an optimal decomposition; and

    recognizing the optimal decomposition via employment of a classifier, wherein the search method employs an optimization method comprising;

    utilizing a cost optimization function to facilitate in segmentation and recognition to determine an optimum grouping and labeling according to Equation (1);


    C([V.sub.i]))=.PHI.(R(V.sub.i),R(V.sub.2), . . . , R(V.sub.n));





    (Eq.

         1)where V.sub.i is a subset of vertices which form a decomposition of an input, R is a best recognition result for the set of vertices, the function .PHI. is a combination cost, and C represents an overall cost of a particular grouping [V.sub.i],wherein the segmentation and recognition process further provides for subsequent correction of the one or more strokes associated with the input generated in a non-linear sequence in time.

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×