Unconstrained handwriting recognition
First Claim
Patent Images
1. A system for recognizing digital image data arranged in rows and columns, comprising:
- a feature extractor for extracting feature information from data representing the rows and columns of the digital image data, wherein the extracted feature information of a row comprises a plurality of row bits and the extracted feature information of a column comprises a plurality of column bits;
a feature compressor for compressing the extracted feature information, whereby a portion of the row bits from the extracted feature information of the rows is removed and a portion of the column bits from the extracted feature information of the columns is removed; and
a neural network for classifying the digital image data from the compressed, extracted feature information.
1 Assignment
0 Petitions
Accused Products
Abstract
Methods and systems of the present invention may be used to recognize digital image data arranged in rows and columns. Exemplary embodiments may include a feature extractor for extracting feature information from data representing the rows and columns of the digital image data, a feature compressor for compressing the extracted feature information, and a neural network for classifying the digital image data from the compressed, extracted feature information.
17 Citations
20 Claims
-
1. A system for recognizing digital image data arranged in rows and columns, comprising:
-
a feature extractor for extracting feature information from data representing the rows and columns of the digital image data, wherein the extracted feature information of a row comprises a plurality of row bits and the extracted feature information of a column comprises a plurality of column bits;
a feature compressor for compressing the extracted feature information, whereby a portion of the row bits from the extracted feature information of the rows is removed and a portion of the column bits from the extracted feature information of the columns is removed; and
a neural network for classifying the digital image data from the compressed, extracted feature information. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. An integrated circuit comprising:
-
a connected component detection array for extracting feature information from data reflecting a digital image of handwritten information;
a feature compressor for compressing the extracted information; and
a neural network for classifying the handwritten information from the compressed information, wherein the neural network includes;
a plurality of neural processing units for processing the compressed information;
an integrator for storing intermediate results from the plurality of neural processing units; and
means for applying transfer functions in the plurality of neural processing units. - View Dependent Claims (14, 15, 16)
-
-
17. A method for recognizing digital image data arranged in rows and columns, comprising:
-
receiving a handwritten symbol; and
processing the handwritten symbol by;
extracting feature information from data representing the rows and columns of the digital image data, wherein the extracted feature information of a row comprises a plurality of row bits and the extracted feature information of a column comprises a plurality of column bits;
compressing the extracted feature information, whereby a portion of the row bits from the extracted feature information of the rows is removed and a portion of the column bits from the extracted feature information of the columns is removed; and
classifying the digital image data from the compressed, extracted feature information. - View Dependent Claims (18)
-
-
19. A computer-readable medium containing instructions to cause a computer to execute the steps of:
-
receiving a handwritten symbol; and
processing the handwritten symbol by;
extracting feature information from data representing the rows and columns of the digital image data, wherein the extracted feature information of a row comprises a plurality of row bits and the extracted feature information of a column comprises a plurality of column bits;
compressing the extracted feature information, whereby a portion of the row bits from the extracted feature information of the rows is removed and a portion of the column bits from the extracted feature information of the columns is removed; and
classifying the digital image data from the compressed, extracted feature information.
-
-
20. A method for recognizing handwritten symbols, comprising:
-
receiving a handwritten symbol; and
processing the handwritten symbol using an integrated circuit, wherein the integrated circuit comprises;
a connected component detection array for extracting feature information from data reflecting a digital image of the handwritten symbol;
a feature compressor for compressing the extracted information; and
a neural network for classifying the handwritten symbol from the compressed information, wherein the neural network includes;
a plurality of neural processing units for processing the compressed information;
a storage medium for storing intermediate results from the plurality of neural processing units; and
means for applying transfer functions in the plurality of neural processing units.
-
Specification