System and methods for providing robust keyword selection in a personal digital notepad

A method for selecting a keyword in a handwriting recording device having an electronic inking stylus and a digitizing tablet associated therewith, wherein the device records stroke data representing handwritten strokes concurrently produced on a writing medium placed over the digitizing tablet using the electronic inking stylus, the method comprising the steps of:

• invoking a keyword selection mode, wherein the keyword selection mode allows a user to designate one or more recorded strokes as a reference keyword;
• accepting as input, handwritten bounding strokes;
• defining a bounding region as the area contained within the handwritten bounding strokes;
• and
• determining keyword membership of a recorded stroke based on a relation between the recorded stroke and the defined bounding region,
• wherein the step of determining keyword membership includes the steps of:
• determining each stroke which is entirely contained and partially contained in the bounding region;
• for each partially contained stroke, calculating a cost factor based on distance from the bounding region of the portion of the partially contained stroke which is outside the bounding region and the percentage of the partially contained stroke which is outside the bounding region;
• comparing each calculated cost factor to a prespecified threshold;
• and
• selecting as keyword members the strokes that are determined to be entirely contained within the bounding region and the partially contained strokes having a calculated cost factor which exceeds the prespecified threshold.

A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform method steps for selecting a keyword in a handwriting recording device, the method steps comprising:

• invoking a keyword selection mode, wherein the keyword selection mode allows a user to designate one or more recorded strokes as a reference keyword;
• accepting as input, handwritten bounding strokes;
• defining a bounding region as the area contained within the handwritten bounding strokes;
• and
• determining keyword membership of a recorded stroke based on a relation between the recorded stroke and the defined bounding region,
• wherein the instructions for determining keyword membership include instructions for performing the steps of:
• determining each stroke which is entirely contained and partially contained in the bounding region;
• for each partially contained stroke, calculating a cost factor based on distance from the bounding region of the portion of the partially contained stroke which is outside the bounding region and the percentage of the partially contained stroke which is outside the bounding region;
• comparing each calculated cost factor to a prespecified threshold;
• and
• selecting as keyword members the strokes that are determined to be entirely contained within the bounding region and the partially contained strokes having a calculated cost factor which exceeds the prespecified threshold.

A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform method steps for selecting a keyword in a handwriting recording device, the method steps comprising:

• invoking a keyword selection mode, wherein the keyword selection mode allows a user to designate one or more recorded strokes as a reference keyword;
• accepting as input, handwritten bounding strokes;
• defining a bounding region as the area contained within the handwritten bounding strokes;
• and
• determining keyword membership of a recorded stroke based on a relation between the recorded stroke and the defined bounding region, wherein the instructions for determining keyword membership include instructions for performing the steps of:
• determining each stroke which is entirely contained and partially contained in the bounding region;
• for each partially contained stroke, calculating a percentage of the stroke contained within the bounding region,
• comparing each calculated percentage to a prespecified threshold;
• and
• selecting as keyword members the strokes that are determined to be entirely contained within the bounding region and the partially contained strokes having a calculated percentage which exceeds the prespecified threshold.