Allograph based writer adaptation for handwritten character recognition

• US 20070140561A1
• Filed: 12/19/2005
• Published: 06/21/2007
• Est. Priority Date: 12/19/2005
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Chellapilla, Kumar, Abdulkader, Ahmad, Simmard, Patrice
• Granted Patent: US 7,646,913 B2
• Time in Patent Office: Days
• US Class Current: 382/187
• CPC Class Codes: G06F 18/231 Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• CPC Class Codes: G06F 18/28 Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
• CPC Class Codes: G06V 10/7625 Hierarchical techniques, i.e. dividing or merging patterns to obtain a tree-like representation; Dendograms
• CPC Class Codes: G06V 10/809 of classification results, e.g. where the classifiers operate on the same input data
• CPC Class Codes: G06V 30/1423 the instrument generating sequences of position coordinates corresponding to handwriting preprocessing or recognising digital ink G06V30/32
• CPC Class Codes: G06V 30/1914 Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries, e.g. user dictionaries
• CPC Class Codes: G06V 30/36 Matching; Classification

Abstract

The claimed subject matter provides a system and/or a method that facilitates analyzing and/or recognizing a handwritten character. An interface component can receive at least one handwritten character. A personalization component can train a classifier based on an allograph related to a handwriting style to provide handwriting recognition for the at least one handwritten character. In addition, the personalization component can employ any suitable combiner to provide optimized recognition.

Claims

1. A system that facilitates analyzing handwriting, comprising:

an interface component that receives at least one handwritten character; and

a personalization component that trains a classifier based on allograph data related to a handwriting style to provide handwriting recognition for the at least one handwritten character.

2. The system of claim 1, further comprising an allograph component that generates allograph data.

3. The system of claim 2, the allograph component automatically generates allograph data utilizing a clustering technique.

4. The system of claim 2, the results of the clustering technique are visualized at least one of a binary tree and a dissimilarity dendogram.

5. The system of claim 3, the clustering technique is a hierarchical agglomerative clustering approach utilizing dynamic time warping as a distance measure.

6. The system of claim 1, further comprising a classifier component that employs a first recognizer that is an allograph neural network (allograph-NN) that utilizes a polynomial feature technique to provide inputs thereto.

7. The system of claim 6, the allograph-NN is trained utilizing allograph data.

8. The system of claim 6, the first recognizer and the allograph-NN utilize at least one of a simple folder, a linear folder, and an allograph folder.

9. The system of claim 6, the classifier component employs a second recognizer that is a base neural network (base-NN) that utilizes a polynomial feature technique to provide inputs thereto.

10. The system of claim 9, the base-NN is trained utilizing non-allograph data.

11. The system of claim 9, further comprising a combine component that can combine the first recognizer output and the second recognizer output.

12. The system of claim 11, the combine component employs at least one of a linear combiner and a linear classifier.

13. The system of claim 11, the combine component employs a combiner classifier that can learn from data.

14. The system of claim 13, the combiner classifier is a support vector machine.

15. The system of claim 14, the support vector machine learns to optimally combine the first recognizer output and the second recognizer output utilizing a handwriting sample from a user.

16. The system of claim 1, the personalization component infers the handwritten character taking in account a deterioration of quality due to fatigue.

17. The system of claim 1, the allograph data can be based at least in part upon at least one of the following:

a geographic region, a school district, a language, and a style of writing.

18. A machine implemented method that facilitates providing handwriting recognition, comprising:

generating allograph data;

training a first classifier utilizing the allograph data; and

providing optimized handwriting recognition for a handwritten character.

19. The method of claim 18, further comprising:

receiving a handwritten character;

creating allograph data automatically and applying a feature vector

training a second classifier with non-allograph data; and

combining the outputs of the first and second classifier utilizing at least one of a linear combiner, a personalizer, a support vector machine (SVM), and a combiner classifier.

20. A machine implemented system that facilitates analyzing handwriting, comprising:

means for receiving at least one handwritten character; and

means for training a classifier based on allograph data related to a handwriting style to provide handwriting recognition for the at least one handwritten character.