Patent US5606629A successfully refreshed from Google Patents.
← Back to Patent Explorer
US5606629A Expired / Lapsed US ⏱️ 0.0 years remaining

Figure recognition apparatus

Assignee: NEC Personal Computers Ltd
•
Filing: 1994-11-15
•
Granted: 1997-02-25
•
Expires: 2014-11-15
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract In a figure recognition apparatus, a direction of a vector starting from a sample point most recently stored in a position data memory and terminating at an attention point is compared to an average value of directions of sample point vectors stored in the position data memory. The result of the comparison is used for deciding whether to discard the attention point.

Inventors

  • 👤 Takahisa Shirakawa

Bibliographic Details

Application Number —
Jurisdiction US
Data Source google_patents
Last Synchronized 2026-11-09 14:21
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/32; G06V30/36; G06V30/373; G06V30/333

Claims Analysis

Total Claims: 11
Claim 1
Independent Claim 459 words
A figure recognition apparatus comprising: a picture input unit for converting a figure of lines into electrical signals; an output unit for a train of points for storing data for a plurality of points, said data at least including position coordinate data for a plurality of points representing said figure of lines in a memory, and for reading out the data for the plurality of points sequentially from said memory; a position data memory for storing at least a predetermined number of sample points; an average vector calculation unit for calculating an average value of directions for a predetermined number of sample point vectors stored in said position data memory, wherein a sample point vector is a vector starting from a sample point of attention and terminating at a sample point immediately following said sample point; a direction difference calculation unit for calculating an absolute value of a direction difference between said average value of directions and a vector starting from a sample point most recently stored in said position data memory and terminating at an attention point, said attention point being defined as a point currently read out from said output unit of a train of points; a discard decision unit for registering an attention point as a sample point in said position data memory when said direction difference of an attention point calculated by said direction difference calculation unit is larger than a predetermined first threshold value Dth1 and smaller than a predetermined second threshold value Dth2; a calculation unit for calculating a feature point probability of each sample point stored in said position data memory, and for selecting feature points from sample points in accordance with said feature point probability; a line type decision unit for deciding, for each feature point, whether a line segment between said feature point and a next feature point is a straight line segment or an arc of a circle; and a figure shape decision unit for deciding a figure shape of said figure of line input from said picture input unit, in accordance with the output of said calculation unit of a feature point probability and said line type decision unit; wherein said calculation unit determines feature point probability of a sample point of attention as an angle between two vectors, one vector of said two vectors starting from a newest sample point of sample points which are older than a sample point of attention having a distance larger than a predetermined value La, and terminating at said sample point of attention, the other vector of said two vectors starting from said sample point of attention and terminating at an oldest sample point of sample points which are newer than said point of attention having a distance larger than La.
Claim 2
Dependent Claim 459 words
A figure recognition apparatus comprising: a picture input unit for converting a figure of lines into electrical signals; an output unit for a train of points for storing data for a plurality of points, said data at least including position coordinate data for a plurality of points representing said figure of lines in a memory, and for reading out the data for the plurality of points sequentially from said memory; a position data memory for storing at least a predetermined number of sample points; an average vector calculation unit for calculating an average value of directions for a predetermined number of sample point vectors stored in said position data memory, wherein a sample point vector is a vector starting from a sample point of attention and terminating at a sample point immediately following said sample point; a direction difference calculation unit for calculating an absolute value of a direction difference between said average value of directions and a vector starting from a sample point most recently stored in said position data memory and terminating at an attention point, said attention point being defined as a point currently read out from said output unit of a train of points; a discard decision unit for registering an attention point as a sample point in said position data memory when said direction difference of an attention point calculated by said direction difference calculation unit is larger than a predetermined first threshold value Dth1 and smaller than a predetermined second threshold value Dth2; a calculation unit for calculating a feature point probability of each sample point stored in said position data memory, and for selecting feature points from sample points in accordance with said feature point probability; a line type decision unit for deciding, for each feature point, whether a line segment between said feature point and a next feature point is a straight line segment or an arc of a circle; and a figure shape decision unit for deciding a figure shape of said figure of line input from said picture input unit, in accordance with the output of said calculation unit of a feature point probability and said line type decision unit; wherein said calculation unit determines feature point probability of a sample point of attention as an angle between two vectors, one vector of said two vectors starting from a newest sample point of sample points which are older than a sample point of attention having a distance larger than a predetermined value La, and terminating at said sample point of attention, the other vector of said two vectors starting from said sample point of attention and terminating at an oldest sample point of sample points which are newer than said point of attention having a distance larger than La.
Claim 3
Dependent Claim 40 words
A figure recognition apparatus of claim 1, wherein said average vector calculation unit determines said average value of directions as the direction of a sample point vector terminating at a sample point most recently stored in said position data memory.
Claim 4
Dependent Claim 44 words
A figure recognition apparatus of claim 1, wherein said average vector calculation unit determines said average value of directions as an average value of directions of sample point vectors for a predetermined number of sample points most recently stored in said position data memory.
Claim 5
Dependent Claim 71 words
A figure recognition apparatus of claim 1, wherein said average vector calculation unit determines said average value of directions as a direction of a vector starting from a sample point which is a newest sample point having a distance larger than a predetermined threshold Lb from a sample point most recently stored in said position data memory, and terminating at said sample point most recently stored in said position data memory.
Claim 6
Dependent Claim 32 words
A figure recognition apparatus of claim 1, wherein said calculation unit of a feature point probability selects sample points having a feature point probability larger than a predetermined threshold as feature points.
Claim 7
Dependent Claim 40 words
A figure recognition apparatus of claim 5, wherein said average vector calculation unit determines said average value of directions as the direction of a sample point vector terminating at a sample point most recently stored in said position data memory.
Claim 8
Dependent Claim 42 words
A figure recognition apparatus of claim 5, wherein said average vector calculation unit determines said average value of directions as an average value of directions of sample point vectors for a predetermined number of sample points stored in said position data memory.
Claim 9
Dependent Claim 71 words
A figure recognition apparatus of claim 5, wherein said average vector calculation unit determines said average value of directions as a direction of a vector starting from a sample point which is a newest sample point having a distance larger than a predetermined threshold Lb from a sample point most recently stored in said position data memory, and terminating at said sample point most recently stored in said position data memory.
Claim 10
Dependent Claim 113 words
A figure recognition apparatus of claim 5, wherein said calculation unit of a feature point probability determines feature point probability of a sample point of attention as an angle between two vectors, the one vector of said two vectors starting from a newest sample point of sample points which are older than said sample point of attention and have a distance larger than a predetermined value La, and terminating at said sample point of attention, the other vector of said two vectors starting from said sample point of attention and terminating at an oldest sample point of sample points which are newer than said sample point of attention having distance larger than La.
Claim 11
Dependent Claim 32 words
A figure recognition apparatus of claim 9, wherein said calculation unit of a feature point probability selects sample points having a feature point probability larger than a predetermined threshold as feature points.

References Cited (Backward Citations)

US4375081A Cited
US4653107A Cited
US4718103A Cited
US4878249A Cited
US5023918A Cited
JPH0462107A Cited

USPTO Annuity & Maintenance Windows

Annuity Stage Window Opens Payment Deadline Surcharge Period Until Estimated Fee Status
3.5 Years (Year 4) 2000-02-25 2000-08-26 2001-02-25 $2000.00 Window Closed / Lapsed
7.5 Years (Year 8) 2004-02-25 2004-08-26 2005-02-25 $3760.00 Window Closed / Lapsed
11.5 Years (Year 12) 2008-02-25 2008-08-26 2009-02-25 $7700.00 Window Closed / Lapsed

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag