Patent US5040230A successfully refreshed from Google Patents.
US5040230A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Associative pattern conversion system and adaptation method thereof
Assignee: Sharp Corp
•
Filing: 1989-01-11
•
Granted: 1991-08-13
•
Expires: 2009-01-11
Abstract
Abstract An associative pattern conversion system is disclosed which may be used for image recognition. The system includes an image input portion, an image processing portion and a recognition portion. The image processing portion includes a process unit for extracting characteristics and a frame memory for holding image data. The recognition portion, which includes a component for the learning of data to be associated, obtains the extracted characteristics from the image processing portion and performs associative pattern conversion from the image input portion. The system of the present invention may be applied to any neutral network, preferably a matrix calculation type neural network.
Inventors
- 👤 Sunao Takatori
- 👤 Ryohei Kumagai
- 👤 Makoto Yamamoto
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-27 14:58
CPC Classifications
G; G06; G06N; G06N3/00; G06N3/02; G06N3/06; G06N3/063; G06V; G06V30/00; G06V30/10; G06V30/19; G06V30/192; G06V30/194
Claims Analysis
Total Claims: 13
Claim 1
Independent Claim
113 words
An associative pattern conversion system comprising: a memory for storing at least an input data, weight data, output data and reference data; weight variable determining means for evaluating a first relationship between said input data and said output data and a second relationship between said input data, said output data and said reference data, said weight variable determining means generating an output; and weight changing means for calculating a variable of said weight data according to said output from said weight variable determining means and said weight data; wherein said weight variable determining means calculates a difference between said output data and said reference data, and multiplies said difference by said input data.
Claim 2
Dependent Claim
113 words
An associative pattern conversion system comprising: a memory for storing at least an input data, weight data, output data and reference data; weight variable determining means for evaluating a first relationship between said input data and said output data and a second relationship between said input data, said output data and said reference data, said weight variable determining means generating an output; and weight changing means for calculating a variable of said weight data according to said output from said weight variable determining means and said weight data; wherein said weight variable determining means calculates a difference between said output data and said reference data, and multiplies said difference by said input data.
Claim 3
Dependent Claim
22 words
An associative pattern conversion system according to claim 1, further comprising an image processing means for extracting characteristics of an input image.
Claim 4
Dependent Claim
62 words
An associative pattern conversion system according to claim 2, wherein said image processing means comprises: a numerical calculation portion for calculating between images a differentiation and having a spatial filter; and a status calculation portion for evaluating a relationship between pixels, for extracting a predetermined pattern and for calculating an identification ratio in accordance with a registered pattern and a predetermined convolution.
Claim 5
Dependent Claim
39 words
An associative pattern conversion system according to claim 1, further comprising: a pattern conversion portion for generating an output pattern in response to data from said memory; and output means for converting said output pattern to an optical signal.
Claim 6
Dependent Claim
17 words
An associative pattern conversion system according to claim 4, wherein said output means multiplexes said output pattern.
Claim 7
Dependent Claim
106 words
An associative pattern conversion system comprising: a memory for storing at least an input data, weight data, output data and reference data; weight variable determining means for evaluating a first relationship between said input data and said output data and a second relationship between said input data, said output data and said reference data, said weight variable determining means generating an output; and weight changing means for calculating a variable of said weight data according to said output from said weight variable determining means and said weight data; wherein said weight changing means adds said output from said weight variable determining means to said weight data.
Claim 8
Dependent Claim
106 words
An associative pattern conversion system comprising: a memory for storing at least an input data, weight data, output data and reference data; weight variable determining means for evaluating a first relationship between said input data and said output data and a second relationship between said input data, said output data and said reference data, said weight variable determining means generating an output; and weight changing means for calculating a variable of said weight data according to said output from said weight variable determining means and said weight data; wherein said weight changing means adds said output from said weight variable determining means to said weight data.
Claim 9
Dependent Claim
120 words
An associative pattern conversion system comprising: a memory for storing at least an input data, weight data, output data and reference data; weight variable determining means for evaluating a first relationship between said input data and said output data and a second relationship between said input data, said output data and said reference data, said weight variable determining means generating an output; and weight changing means for calculating a variable of said weight data according to said output from said weight variable determining means and said weight data; wherein said weight changing means multiplies said output from said weight variable determining means by an efficiency value according to said weight data and adds said weight data to said multiplication result.
Claim 10
Dependent Claim
120 words
An associative pattern conversion system comprising: a memory for storing at least an input data, weight data, output data and reference data; weight variable determining means for evaluating a first relationship between said input data and said output data and a second relationship between said input data, said output data and said reference data, said weight variable determining means generating an output; and weight changing means for calculating a variable of said weight data according to said output from said weight variable determining means and said weight data; wherein said weight changing means multiplies said output from said weight variable determining means by an efficiency value according to said weight data and adds said weight data to said multiplication result.
Claim 11
Dependent Claim
22 words
An associative pattern conversion system according to claim 7, wherein said efficiency value is determined in accordance with a monotonous decreasing function.
Claim 12
Dependent Claim
18 words
An associative pattern conversion system according to claim 7, wherein said efficiency value is determined by a table.
Claim 13
Dependent Claim
14 words
An associative pattern conversion system according to claim 9, wherein said table is rewritable.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1994-08-12 | 1995-02-11 | 1995-08-13 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1998-08-12 | 1999-02-11 | 1999-08-13 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2002-08-12 | 2003-02-11 | 2003-08-13 | $7700.00 | Window Closed / Lapsed |