International Business Machines Corporation

Krishna Sundaram Nathan

David Nahamoo

Jerome R Bellegarda

John Peter Karidis

Eveline J Bellegarda

Ronald A Smith

Michael Peter Perrone

Robert Edward Steinbugler

Eugene Henry Ratzlaff

Gregory J Clary

Jayashree Subrahmonia

John Ferdinand Pitrelli

Tetsunosuke Fujisaki

Peter Dirk Hortensius

Robert Joseph Evans

Thomas Allan Corbi

Systems and methods are described for concisely encoding into a lexicon (or dictionary) and decoding from the lexicon regular expressions that can represent certain huge word lists that might otherwise be considered unmanageably large. Sets of words (character sequences or 'strings') that share certain commonalities such as a set of numbers, which share common digits, may be condensed into digital lexicons by representing the set with a regular expression. The regular expression is a string that includes meta-character, where each meta-character is a place-marker that represents a set of at least two normal characters. When accessing or searching the lexicon, the regular expressions are dynamically expanded, as needed, to the underlying, original word list. The methods disclosed are applicable to many lexicon driven language based systems such as spelling verification systems, handwriting recognition systems, speech recognition systems and the like.

Method for encoding regular expressions in a lexigon

A flexibly interfaceable portable computing device includes a display coupled to a processor, which is coupled or selectively coupled to either or both of a keyboard and a recording unit. The display and the keyboard provide a first user interface to the processor. The recording unit is superimposable with a removable markable surface. A stylus allows user marking on the markable surface. The stylus provides a stroke signal and a stroke mark. The recording unit, the markable surface, and the stylus provide a second user interface to the processor. Optionally, the display also contributes to providing the second user interface to the processor. Switching among viewing modes for the display, and synchronization of information between the processor and a processor of the recording unit are also provided. A casing can enfold the display, the keyboard, and the recording unit to form a relatively slim profile. A portable computer system can have a display, a keyboard, and thick components enfolded and/or located within an overall thickness substantially equal to a sum of a first thickness for the display plus a second thickness for the keyboard, to present a slim profile.

Flexibly interfaceable portable computing device

A handwriting recognition system and method whereby various character sequences (which are typically &ldquo;slurred&rdquo; together when handwritten) are each modelled as a single character (&ldquo;compound character model&rdquo;) so as to provide increased decoding accuracy for slurred handwritten character sequences. In one aspect of the present invention, a method for generating a handwriting recognition system having compound character models comprises the steps of: providing an initial handwriting recognition system having individual character models; collecting and labelling a set of handwriting data; aligning the labelled set of handwriting data; generating compound character data using the aligned handwriting data; and retraining the initial recognition system with the compound character data to generate a new recognition system having compound character models. Once these compound character models are trained, they may be used to accurately decode slurred handwritten character sequences for which compound character models were previously generated. Once recognized, the compound characters are expanded into the constituent individual characters comprising the compound character.

Handwriting recognition system and method using compound characters for improved recognition accuracy

System and methods for visually displaying page information in a handwriting recording device such as a personal digital notepad (PDN) device, in which constraints exist which limit the size of a user interface display (e.g. LCD). Various methods allow a user to view detailed page information by selecting one or more available display modes which display the selected information using one or more dynamic icons. In addition, the user can view (via the display) selected portions of handwriting content of a given electronic page, thereby affording the user the opportunity to synchronize the stored handwriting data with the handwritten text.

System and method for displaying page information in a personal digital notepad

Real time digitization of handwritten text and integration of digital recordation of handwritten text with traditional paper-based record making systems is achieved with a recording unit which may record a sequential data stream of strokes and associated events. The data stream may be stored in the apparatus and processed in accordance with various applications. Recordation of handwritten strokes may be accompanied by automatic detection and recordation of predefined events, and by user invoked generation of events. Recorded handwritten text may be processed to produce character strings or image data for text recorded in conjunction with predefined events.

Methods, systems and products pertaining to a digitizer for use in paper based record systems

A method of training a writer dependent handwriting recognition system with handwriting samples of a specific writer comprises the steps of: capturing the handwriting samples of the specific writer; segmenting the handwriting samples of the specific writer; initializing handwriting models associated with the specific writer from the segmented handwriting samples; and refining the initialized handwriting models associated with the specific writer to generate writer dependent handwriting models for use by the writer dependent handwriting recognition system. Preferably, the method also comprises the step of repeating the refining step until the writer dependent handwriting models yield recognition results substantially satisfying a predetermined accuracy threshold.

Methods and apparatus for customizing handwriting models to individual writers

A scheduling facilitation system includes a recording unit, a markable surface (e.g., a template), and a stylus. The recording unit includes a memory, a logic design implementation (e.g., software and/or hardware), and a working surface. The memory stores an electronic representation of a schedule. The logic design implementation serves to correlate the working surface to the schedule. The working surface is superimposed with the markable surface. A stylus stroke signal (e.g., a first radio frequency) conveys to the recording unit scheduling information for a selected entry location of the schedule. A stylus stroke mark (e.g., ink) concurrently conveys to the markable surface the scheduling information. The memory stores the scheduling information. A check signal (e.g., a second radio frequency and/or a soft button activation) can search for scheduling opening(s) and/or conflict(s).

Thinkscribe combined electronic and paper based scheduling

An automatic handwriting recognition system wherein each written (chirographic) manifestation of each character is represented by a statistical model (called a hidden Markov model). The system implements a method which entails sampling a pool of independent writers and deriving a hidden Markov model for each particular character (allograph) which is independent of a particular writer. The HMMs are used to derive a chirographic label alphabet which is independent of each writer. This is accomplished during what is described as the training phase of the system. The alphabet is constructed using supervised techniques. That is, the alphabet is constructed using information learned in the training phase to adjust the result according to a statistical algorithm (such as a Viterbi alignment) to arrive at a cost efficient recognition tool. Once such an alphabet is constructed a new set of HMMs can be defined which more accurately reflects parameter typing across writers. The system recognizes handwriting by applying an efficient hierarchical decoding strategy which employs a fast match and a detailed match function, thereby making the recognition cost effective.

System and method for automatic handwriting recognition with a

A computer-based system and method for recognizing handwriting. The present invention includes a pre-processor, a front end, and a modeling component. The present invention operates as follows. First, the present invention identifies the lexemes for all characters of interest. Second, the present invention performs a training phase in order to generate a hidden Markov model for each of the lexemes. Third, the present invention performs a decoding phase to recognize handwritten text. Hidden Markov models for lexemes are produced during the training phase. The present invention performs the decoding phase as follows. The present invention receives test characters to be decoded (that is, to be recognized). The present invention generates sequences of feature vectors for the test characters by mapping in chirographic space. For each of the test characters, the present invention computes probabilities that the test character can be generated by the hidden Markov models. The present invention decodes the test character as the recognized character associated with the hidden Markov model having the greatest probability.

Continuous parameter hidden Markov model approach to automatic

Methods and apparatus are disclosed for recognizing handwritten characters in response to an input signal from a handwriting transducer. A feature extraction and reduction procedure is disclosed that relies on static or shape information, wherein the temporal order in which points are captured by an electronic tablet may be disregarded. A method of the invention generates and processes the tablet data with three independent sets of feature vectors which encode the shape information of the input character information. These feature vectors include horizontal (x-axis) and vertical (y-axis) slices of a bit-mapped image of the input character data, and an additional feature vector to encode an absolute y-axis displacement from a baseline of the bit-mapped image. It is shown that the recognition errors that result from the spatial or static processing are quite different from those resulting from temporal or dynamic processing. Furthermore, it is shown that these differences complement one another. As a result, a combination of these two sources of feature vector information provides a substantial reduction in an overall recognition error rate. Methods to combine probability scores from dynamic and the static character models are also disclosed.

Automatic handwriting recognition using both static and dynamic

A computer-based system and method for recognizing handwriting. The present invention includes a preprocessor, a front end, and a modeling component. The present invention operates as follows. First, the present invention identifies the lexemes for all characters of interest. Second, the present invention performs a training phase in order to generate a hidden Markov model for each of the lexemes. Third, the present invention performs a decoding phase to recognize handwritten text. Hidden Markov models for lexemes are produced during the training phase. The present invention performs the decoding phase as follows. The present invention receives test characters to be decoded (that is, to be recognized). The present invention generates sequences of feature vectors for the test characters by mapping in chirographic space. For each of the test characters, the present invention computes probabilities that the test character can be generated by the hidden Markov models. The present invention decodes the test character as the recognized character associated with the hidden Markov model having the greatest probability.

Growing community of inventors

New York, NY, United States of America

Krishna Sundaram Nathan