US5295197A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Information processing system using neural network learning function
Assignee: Hitachi Ltd
•
Filing: 1991-10-11
•
Granted: 1994-03-15
•
Expires: 2011-10-11
Abstract
Abstract An information processing apparatus using a neural network learning function has, in one embodiment, a computer system and a pattern recognition apparatus associated with each other via a communication cable. The computer system includes a learning section having a first neural network and serves to adjust the weights of connection therein as a result of learning with a learning data signal supplied thereto from the pattern recognition apparatus via the communication cable. The pattern recognition apparatus includes an associative output section having a second neural network and receives data on the adjusted weights from the learning section via the communication cable to reconstruct the second neural network with the data on the adjusted weights. The pattern recognition apparatus with the associative output section having the reconstructed second neural network performs pattern recognition independently of the computer system with the communication cable being brought into an electrical isolation mode.
Inventors
- 👤 Hiroshi Takenaga
- 👤 Yoshiyuki Okuyama
- 👤 Masao Takatoo
- 👤 Kazuyoshi Asada
- 👤 Norio Tanaka
- 👤 Tadaaki Kitamura
- 👤 Kuniyuki Kikuchi
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-02 18:17
CPC Classifications
G; G06; G06N; G06N3/00; G06N3/02; G06N3/08; G06N3/084; G06N3/04; G06N3/044; G06N3/0442; G06N3/045; G06N3/0499; G06N3/082; G06N3/09; G06V; G06V30/00; G06V30/10; G06V30/19; G06V30/192; G06V30/194
Claims Analysis
Total Claims: 7
Claim 1
Independent Claim
136 words
An apparatus for inspecting an object, said apparatus comprising an image input section for detecting an image of an object; an image processing section for extracting image data from the detected image, the image data being indicative of the inspected object; a neuro-learning section, including a first neural network, for receiving the extracted image data and learning data for the first neural network, and for determining weights in the first neural network; a neuro-associative output section, including a second neural network, for constructing said second neural network on the basis of the weights determined by the neuro-learning section, and for producing an associative output for the image data applied thereto; and a discriminator section for determining the degree of perfection or imperfection of the object on the basis of the output from the neuro-associative output section.
Claim 2
Independent Claim
136 words
An apparatus for inspecting an object, said apparatus comprising an image input section for detecting an image of an object; an image processing section for extracting image data from the detected image, the image data being indicative of the inspected object; a neuro-learning section, including a first neural network, for receiving the extracted image data and learning data for the first neural network, and for determining weights in the first neural network; a neuro-associative output section, including a second neural network, for constructing said second neural network on the basis of the weights determined by the neuro-learning section, and for producing an associative output for the image data applied thereto; and a discriminator section for determining the degree of perfection or imperfection of the object on the basis of the output from the neuro-associative output section.
Claim 3
Dependent Claim
88 words
An image inspection apparatus for determining the degree of perfection or imperfection of an object by use of image information, said apparatus comprising a neural network; means for applying the image information of a perfect object to the neural network as learning data; means for supplying the neural network with the image information of an inspected object, thereby to produce an associative output; and means for determining the degree of perfection or imperfection of the object in accordance with the magnitude of output neurons providing the associative output;
Claim 4
Dependent Claim
88 words
An image inspection apparatus for determining the degree of perfection or imperfection of an object by use of image information, said apparatus comprising a neural network; means for applying the image information of a perfect object to the neural network as learning data; means for supplying the neural network with the image information of an inspected object, thereby to produce an associative output; and means for determining the degree of perfection or imperfection of the object in accordance with the magnitude of output neurons providing the associative output;
Claim 5
Dependent Claim
85 words
An image inspection apparatus according to claim 1, wherein said neuro-learning section prepares as many output neurons of an output layer of the first neural network as the categories of objects for inspection; and said discriminator section determines that an object is perfect when the maximum value of the output neurons is larger than a predetermined first threshold and at the same time the ratio of the second largest value of the output neurons to said maximum value is larger than a predetermined second threshold.
Claim 6
Dependent Claim
25 words
An image inspection apparatus according to claim 2, wherein the object is a printer, and the image information is a character produced by the printer.
Claim 7
Dependent Claim
34 words
An image inspection apparatus according to claim 2, wherein the object is a selected one of a product, a part and a material; and the image information is the appearance of the selected one.
References Cited (Backward Citations)
US5052043A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1997-03-14 | 1997-09-13 | 1998-03-15 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2001-03-14 | 2001-09-13 | 2002-03-15 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2005-03-14 | 2005-09-13 | 2006-03-15 | $7700.00 | Window Closed / Lapsed |