§
Luxuse
Patent Intelligence
Sign In
Patent US3348774A successfully refreshed from Google Patents.
Patent US4162482A successfully refreshed from Google Patents.
← Back to Patent Explorer
US4162482A Expired / Lapsed US ⏱️ 0.0 years remaining

Pre-processing and feature extraction system for character recognition

Assignee: Unisys Corp
•
Filing: 1977-12-07
•
Granted: 1979-07-24
•
Expires: 1997-12-07
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract Character recognition apparatus and a method for identifying machine-printed and hand-printed characters. A character is optically scanned and converted to a rectangular matrix representation containing black and white points. The matrixed character is pre-processed by a non-iterative line-thinning technique so as to reduce the stroke width to no more than two points along the center line of the matrixed character. Isolated black points formed in the process of thinning the strokes are removed. Any gaps in the center-line of the matrixed character are filled and the edges of all long strokes are smoothed. The thinned character matrix is divided into a plurality of regions. One of a set of predetermined stroke features of the character matrix is extracted by scanning subregions of the character matrix such that the center position of the scanned subregions will have occupied all elements of the character matrix after one complete scan. A particular stroke feature is identified by an analysis of the arrangement of black and white points detected in each subregion. The feature extracted will be assigned to the region containing the center position of the particular subregion which was scanned. The features extracted in each of the regions are used to identify the character. In one embodiment, the sequence of stroke features detected for regions of the character matrix is compared with a table of stroke sequences corresponding to previously identified characters. The matrix is assigned to the character whose stroke sequences most closely match that of the matrixed character. Alternatively, a weighted value may be assigned to each of the possible stroke features in each region for every possible character, based on the relative importance of that feature to the character in that region, as determined by analysis of previously identified samples of the particular hand-printed or machine-printed characters. The matrixed character is identified by summing the weighted values of the detected features assigned to each region to produce a score for each character matrix. The matrix is then assigned to the character yielding the highest score.

Inventors

  • 👤 Chauchang Su

Bibliographic Details

Application Number —
Jurisdiction US
Data Source google_patents
Last Synchronized 2026-10-23 19:19
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/20

Claims Analysis

Total Claims: 13
Claim 1
Independent Claim 297 words
Apparatus for machine recognition of hand-written or machine printed characters comprising: means for scanning said character; means for generating a matrix of black and white points from said scanned character, said matrix being stored in a storage shift register; means for non-iteratively thinning said matrixed character to generate a centerline representative of said matrixed character; means for removing isolated points in said thinned character matrix; means for filling in discontinuities appearing in said centerline of said matrixed character; means for removing spurious points adjoining said centerline of said matrixed character; means for partitioning said thinned character matrix into a plurality of regions; means for scanning a plurality of areas of said regions, each of said areas comprising a plurality of subregions, wherein said scanned areas overlap a plurality of said regions and wherein said areas each have a center point; means for detecting a pattern of black and white points in each of said scanned areas; means for generating a unique coded value representative of said detected pattern in each of said scanned areas; means for comparing said coded value with a known set of values corresponding to geometrical stroke features until a match is detected; means for generating an output signal indicative of the detection of one of said stroke features, in each of said scanned areas; means for assigning said detected stroke feature to said area containing said center element of each of said scanned areas; means for detecting sequentially said assigned stroke features for each of said plurality of regions; means for comparing said sequentially detected stroke features with a known set of sequences corresponding to characters previously identified; and means for assigning said matrixed character to said previously identified character having stroke sequences most closely corresponding to those detected form said matrixed character.
Claim 2
Dependent Claim 297 words
Apparatus for machine recognition of hand-written or machine printed characters comprising: means for scanning said character; means for generating a matrix of black and white points from said scanned character, said matrix being stored in a storage shift register; means for non-iteratively thinning said matrixed character to generate a centerline representative of said matrixed character; means for removing isolated points in said thinned character matrix; means for filling in discontinuities appearing in said centerline of said matrixed character; means for removing spurious points adjoining said centerline of said matrixed character; means for partitioning said thinned character matrix into a plurality of regions; means for scanning a plurality of areas of said regions, each of said areas comprising a plurality of subregions, wherein said scanned areas overlap a plurality of said regions and wherein said areas each have a center point; means for detecting a pattern of black and white points in each of said scanned areas; means for generating a unique coded value representative of said detected pattern in each of said scanned areas; means for comparing said coded value with a known set of values corresponding to geometrical stroke features until a match is detected; means for generating an output signal indicative of the detection of one of said stroke features, in each of said scanned areas; means for assigning said detected stroke feature to said area containing said center element of each of said scanned areas; means for detecting sequentially said assigned stroke features for each of said plurality of regions; means for comparing said sequentially detected stroke features with a known set of sequences corresponding to characters previously identified; and means for assigning said matrixed character to said previously identified character having stroke sequences most closely corresponding to those detected form said matrixed character.
Claim 3
Dependent Claim 82 words
The apparatus of claim 1 wherein said means for thinning said matrixed character to generate a centerline comprises a non-iterative line-thinning circuit, said circuit including: means for scanning elemental areas of said matrixed characters, said elemental areas each having a center element; means for detecting a pattern of black and white points in each of said elemental areas; and means for setting said center element in each of said elemental areas to black if a plurality of surrounding elements are also black.
Claim 4
Dependent Claim 15 words
The apparatus of claim 2 wherein said elemental areas each comprise a 7×7 element array.
Claim 5
Dependent Claim 79 words
The apparatus of claim 1 wherein said means for removing isolated points in said character matrix comprises a noise removal circuit, said circuit including: means for scanning elemental areas of said matrixed character, said elemental areas each having a center element; means for detecting a pattern of black and white points in each of said elemental areas; and means for setting said center element in each of said elemental areas to white if all surrounding elements are also white.
Claim 6
Dependent Claim 15 words
The apparatus of claim 4 wherein said elemental areas each comprise a 3×3 element array.
Claim 7
Dependent Claim 91 words
The apparatus of claim 1 wherein said means for filling in discontinuities appearing in said center of line in said matrixed character comprises a connectivity circuit, said circuit including: means for scanning elemental areas of said matrixed character, said elemental areas each having a center zone comprising a plurality of points; means for detecting a pattern of black and white points in each of said elemental areas; and means for setting said central zone in each of said elemental areas to black if a plurality of surrounding elements are also black.
Claim 8
Dependent Claim 15 words
The apparatus of claim 6 wherein said elemental areas each comprise a 3×5 element array.
Claim 9
Dependent Claim 102 words
The apparatus of claim 1 wherein said means for removing spurious points adjoining said centerline of said matrixed character comprises an edge smoothing circuit, said circuit including: means for scanning elemental areas of said matrixed character, said elemental areas each having a central section comprising a rectangular array of a plurality of points; means for detecting a pattern on black and white points adjoining said central section in each of said elemental areas; and means for setting said central section in each of said elemental areas to white if said central section is surrounded on at least three sides by white points.
Claim 10
Dependent Claim 15 words
The apparatus of claim 8 wherein said elemental areas each comprise a 6×6 element array.
Claim 11
Dependent Claim 15 words
The apparatus of claim 8 wherein said central sections each comprise a 2×2 element array.
Claim 12
Dependent Claim 16 words
The apparatus of claim 1 wherein each of said scanned areas comprise a 6×6 element array.
Claim 13
Dependent Claim 18 words
The apparatus of claim 11 wherein each said subregion of said scanned areas comprise a 2×2 element array.

References Cited (Backward Citations)

US3196398A Cited
US3339179A Cited
US3541511A Cited
US3846754A Cited
US3930231A Cited
US4061998A Cited
US4003024A Cited

USPTO Annuity & Maintenance Windows

Annuity Stage Window Opens Payment Deadline Surcharge Period Until Estimated Fee Status
3.5 Years (Year 4) 1982-07-23 1983-01-22 1983-07-24 $2000.00 Window Closed / Lapsed
7.5 Years (Year 8) 1986-07-23 1987-01-22 1987-07-24 $3760.00 Window Closed / Lapsed
11.5 Years (Year 12) 1990-07-23 1991-01-22 1991-07-24 $7700.00 Window Closed / Lapsed

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag