Patent EP0487309A2 successfully refreshed from Google Patents.
EP0487309A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Pattern recognition method and apparatus using a neural network
Assignee: Canon Inc
•
Filing: 1991-11-19
•
Granted: —
•
Expires: 2011-11-19
Abstract
Abstract A method and apparatus for using a neural network to categorize patterns from pattern feature data derived from the patterns. The average of all the learning data of the neural network is subtracted from the pattern feature data, and the result is input to the input layer of the neural network. The neural network outputs a value for each category and the pattern is categorized based on these values. The neural network includes an intermediate layer whose bias is set to zero and which includes a sigmoid transfer function which is symmetric with respect to the origin.
Inventors
- 👤 Toru C/O Canon Kabushiki Kaisha Niki
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-09 14:41
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/19; G06V30/192; G06V30/194
Claims Analysis
Total Claims: 12
Claim 1
Independent Claim
49 words
A method for processing input data for a neural network provided with learning data, the method comprising the steps of: producing an average value of the learning data; subtracting the average value from the input data to obtain difference data; and supplying the difference data to the neural network.
Claim 2
Dependent Claim
34 words
A method according to Claim 1, wherein said neural network includes at least one intermediate layer, and further comprising the steps of setting a bias for the at least one intermediate layer to zero.
Claim 3
Dependent Claim
23 words
A method according to Claim 1, wherein said neural network includes a sigmoid transfer function which is symmetric with respect to the origin.
Claim 4
Independent Claim
74 words
A method for categorizing input data into one of plural categories using a neural network provided with learning data, said method comprising the steps of: producing an average value of the learning data; subtracting the average value from the input data to obtain difference data; supplying the difference data to the neural network; receiving a value corresponding to each category from the neural network; and categorizing the input data based on the received values.
Claim 5
Dependent Claim
34 words
A method according to Claim 4, wherein said neural network includes at least one intermediate layer, and further comprising the steps of setting a bias for the at least one intermediate layer to zero.
Claim 6
Dependent Claim
23 words
A method according to Claim 4, wherein said neural network includes a sigmoid transfer function which is symmetric with respect to the origin.
Claim 7
Dependent Claim
114 words
A pattern recognition apparatus for categorizing a pattern into one of plural categories, comprising: feature extracting means for extracting feature data from the pattern; storing means for storing an average value; subtracting means for subtracting the average value in the storing means from the feature data extracted by the feature extracting means to form difference data; a neural network provided with learning data, said neural network receiving the difference data and outputting a value for each of the plural categories, wherein the average value stored in said storing means is the average value of the learning data; and categorizing means for categorizing the pattern on the basis of the outputs from the neural network.
Claim 8
Dependent Claim
34 words
An apparatus according to Claim 7, wherein said neural network includes at least one intermediate layer, and further comprising the steps of setting a bias for the at least one intermediate layer to zero.
Claim 9
Dependent Claim
23 words
An apparatus according to Claim 7, wherein said neural network includes a sigmoid transfer function which is symmetric with respect to the origin.
Claim 10
Dependent Claim
96 words
A neural network provided with learning data for categorizing input data into one of plural categories, comprising: an input layer for inputting a value obtained by subtracting from the input data an average value of the learning data; at least one intermediate layer for processing data from the input layer, said at least one intermediate layer having a bias set to zero and a sigmoid transfer function which is symmetric with respect to the origin; and an output layer for receiving data from said at least one intermediate layer and outputting a value for each category.
Claim 11
Dependent Claim
142 words
A pattern recognition apparatus for categorizing a visually perceptible pattern into one of plural categories, comprising: converting means for converting the visually perceptible pattern into an electrical signal; preprocessing means for normalizing and binarizing the electrical signal; feature extracting means for extracting feature data from the normalized and binarized electrical signal; storing means for storing an average; subtracting means for subtracting the average stored in said storing means from the feature data extracted by said feature extracting means to form difference data; a neural network provided with learning data for receiving the difference data and for outputting a value for each of the plural categories, wherein the average value stored in said storing means is the average value of the learning data; and outputting means for outputting one of the plural categories on the basis of the outputs from said neural network.
Claim 12
Dependent Claim
50 words
A processing system having a neural network provided with learning data, characterised by means (101) for storing an average value of said learning data; and difference means (105) for determining the difference between said input data and said average value and for supplying said difference data to said neural network.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.