Training an on-line handwriting recognizer
First Claim
1. A method for creating character model graphs for an on-line recognizer of handwritten text, the method comprising:
- generating character model graphs from typical shapes of characters, the character model graphs having a set of adjustable parameters;
recognizing sample words in a work set using the character model graphs;
evaluating a recognition error for a sample word;
calculating a gradient of the recognition error;
adjusting the adjustable parameters of the character model graphs to provide an updated set of the adjustable parameters, based on at least one of the recognition error and the gradient of the recognition error;
recognizing test words in a test set using character model graphs with the updated set of adjustable parameters;
calculating a correct recognition value for the test set when using the model graphs with the updated set of adjustable parameters;
iterating the above sequence of acts until the correct recognition value reaches an optimum value; and
selecting the updated set of adjustable parameters yielding the correct recognition value having the optimum value as the set of adjustable parameters to be used in character model graphs.
11 Assignments
0 Petitions
Accused Products
Abstract
Character model graphs are created, and the parameters of the model graphs are adjusted to optimize character recognition performed with the model graphs. In effect the character recognizer using the model graphs is trained. The model graphs are created in three stages. First, a vector quantization process is used on a set of raw samples of handwriting symbols to create a smaller set of generalized reference characters or symbols. Second, a character reference model graph structure is created by merging each generalized form model graph of the same character into a single character reference model graph. The merging is based on weighted Euclidian distance between parts of trajectory assigned to graph edges. As a last part of this second stage “type-similarity” vectors are assigned to model edges to describe similarities of given model edge to each shape and to each possible quantized value of other input graph edge parameters. Thus, similarity functions, or similarity values, are defined by different tables on different model edges. In the third stage, model creation further consists of minimizing recognition error by adjusting model graphs parameters. An appropriate smoothing approximation is used in the calculation of similarity score between input graph and model graphs. The input graph represents a word from a work sample set used for training, i.e. adjusting the model graph parameters. A recognition error is calculated as a function of the difference between similarity scores for best answers and the one correct answer for the word being recognized. The gradient of the recognition error as a function of change in parameters is computed and used to adjust the parameters. Model graphs with adjusted parameters are then used to recognize the words in a test set, and a percent of correct recognitions in the test set is calculated. The recognition error calculation with the work set, the parameter adjustment process, and the calculation of the percent of correct recognitions with the test set is repeated. After a number of iterations of this process, the optimum set of parameters for the model graphs will be found.
-
Citations
29 Claims
-
1. A method for creating character model graphs for an on-line recognizer of handwritten text, the method comprising:
-
generating character model graphs from typical shapes of characters, the character model graphs having a set of adjustable parameters; recognizing sample words in a work set using the character model graphs; evaluating a recognition error for a sample word; calculating a gradient of the recognition error; adjusting the adjustable parameters of the character model graphs to provide an updated set of the adjustable parameters, based on at least one of the recognition error and the gradient of the recognition error; recognizing test words in a test set using character model graphs with the updated set of adjustable parameters; calculating a correct recognition value for the test set when using the model graphs with the updated set of adjustable parameters; iterating the above sequence of acts until the correct recognition value reaches an optimum value; and selecting the updated set of adjustable parameters yielding the correct recognition value having the optimum value as the set of adjustable parameters to be used in character model graphs. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A system for optimizing character model graphs comprising:
-
a first recognition module to recognize sample words from a work set using character model graphs defined by a parameter set, the first recognition module is to generate recognition error information for the work set and to adjust the parameters in the parameter set based on the recognition error information; a second recognition module coupled to the first recognition module, to recognize test words from a test set with character model graphs using the adjusted parameter set, and to generate a correct recognition value for the test set based on correct recognition of the test words in the test set; and an iteration module coupled to the first and second recognition modules, to repeatedly execute the first recognition module and the second recognition module until the correct recognition value reaches an optimum value. - View Dependent Claims (10, 11, 12, 13, 14)
-
-
15. A computer readable medium for storing computer instructions for a computer process for training character model graphs to optimize the recognition of text by a recognizer using the character model graphs, the computer process comprising:
-
recognizing words from a first set of words using a current parameter set for the character model graphs and generating a recognition error gradient for the first set based on changes in the word recognition error as a function of changes in parameters in the current parameter set of the character model graphs; adjusting the parameters of the character model graphs in response to the recognition error gradient to create an updated parameter set for the character model graphs; recognizing words from a second set of words using the updated parameter set and generating a correct recognition value, the correct recognition value being associated with the updated parameter set for the character model graphs; and repeating all of the above acts until the correct recognition value reaches a transition value and selecting the parameter set associated with the transition value as the optimum parameters for the character model graphs. - View Dependent Claims (16, 17, 18, 19, 20)
-
-
21. A method for creating character model graphs for a set of reference characters for use by a character recognizer, the method comprising:
-
determining a plurality of typical character shapes for a reference character; creating a character shape model graph for each typical character shape of the reference character; merging a plurality of the character shape model graphs for the reference character into a single character model graph by compressing data for the plurality of the character shape model graphs; and repeating the determining, the creating and the merging for each reference character to create the character model graphs for the set of the reference characters for the character recognizer. - View Dependent Claims (22)
-
-
23. A method for creating character model graphs of reference characters for use by a character recognizer, the method comprising:
-
determining a predetermined number of typical character shapes for a reference character; creating a character shape model graph for each typical character shape of the reference character; merging all character shape model graphs for the reference character into a single character model graph; and repeating the determining, the creating and the merging for each reference character to create character model graphs for the reference characters for use by the character recognizer, wherein the edges of each model graph are described as a vectors of cosine coefficients. - View Dependent Claims (24, 25, 26, 27, 28, 29)
-
Specification