Showing papers on "Handwriting recognition published in 1994"

Comparison of classifier methods: a case study in handwritten digit recognition

Abstract: This paper compares the performance of several classifier algorithms on a standard database of handwritten digits. We consider not only raw accuracy, but also training time, recognition time, and memory requirements. When available, we report measurements of the fraction of patterns that must be rejected so that the remaining patterns have misclassification rates less than a given threshold.

UNIPEN project of on-line data exchange and recognizer benchmarks

Abstract: We report the status of the UNIPEN project of data exchange and recognizer benchmarks started two years ago at the initiative of the International Association of Pattern Recognition (Technical Committee 11). The purpose of the project is to propose and implement solutions to the growing need of handwriting samples for online handwriting recognizers used by pen-based computers. Researchers from several companies and universities have agreed on a data format, a platform of data exchange and a protocol for recognizer benchmarks. The online handwriting data of concern may include handprint and cursive from various alphabets (including Latin and Chinese), signatures and pen gestures. These data will be compiled and distributed by the Linguistic Data Consortium. The benchmarks will be arbitrated the US National Institute of Standards and Technologies. We give a brief introduction to the UNIPEN format. We explain the protocol of data exchange and benchmarks.

Handwriting signal processing front-end for handwriting recognizers

Abstract: A handwriting signal processing front-end method and apparatus for a handwriting training and recognition system which includes non-uniform segmentation and feature extraction in combination with multiple vector quantization. In a training phase, digitized handwriting samples are partitioned into segments of unequal length. Features are extracted from the segments and are grouped to form feature vectors for each segment. Groups of adjacent from feature vectors are then combined to form input frames. Feature-specific vectors are formed by grouping features of the same type from each of the feature vectors within a frame. Multiple vector quantization is then performed on each feature-specific vector to statistically model the distributions of the vectors for each feature by identifying clusters of the vectors and determining the mean locations of the vectors in the clusters. Each mean location is represented by a codebook symbol and this information is stored in a codebook for each feature. These codebooks are then used to train a recognition system. In the testing phase, where the recognition system is to identify handwriting, digitized test handwriting is first processed as in the training phase to generate feature-specific vectors from input frames. Multiple vector quantization is then performed on each feature-specific vector to represent the feature-specific vector using the codebook symbols that were generated for that feature during training. The resulting series of codebook symbols effects a reduced representation of the sampled handwriting data and is used for subsequent handwriting recognition.

T-Cube: a fast, self-disclosing pen-based alphabet

Abstract: An interface for entering text to a pen-based computer is described. The technique proposes a new alphabet, where each letter is a flick gesture. These flick gestures are selfdisclosing using pie menus. An experiment determined the speeds of executing the flick gestures and the transition speeds between gestures. An assignment of characters to gestures is developed and evaluated. Audio feedback is used to convey whether a gesture was wellor badly-formed. A longitudinal study showed clear progress on a learning curve. The method is compared to soft keyboards, handwriting recognition systems, and unistrokes.

Pairwise Neural Network Classifiers with Probabilistic Outputs

Abstract: Multi-class classification problems can be efficiently solved by partitioning the original problem into sub-problems involving only two classes: for each pair of classes, a (potentially small) neural network is trained using only the data of these two classes. We show how to combine the outputs of the two-class neural networks in order to obtain posterior probabilities for the class decisions. The resulting probabilistic pairwise classifier is part of a handwriting recognition system which is currently applied to check reading. We present results on real world data bases and show that, from a practical point of view, these results compare favorably to other neural network approaches.

On-line cursive script recognition using time delay neural networks and hidden Markov models

Abstract: Presents a writer independent system for on-line handwriting recognition which can handle both cursive script and hand-print. The pen trajectory is recorded by a touch sensitive pad, such as those used by note-pad computers. The input to the system contains the pen trajectory information, encoded as a time-ordered sequence of feature vectors. Features include X and Y coordinates, pen-lifts, speed, direction and curvature of the pen trajectory. A time delay neural network with local connections and shared weights is used to estimate a posteriori probabilities for characters in a word. A hidden Markov model segments the word into characters in a way which optimizes the global word score, taking a dictionary into account. A geometrical normalization scheme and a fast but efficient dictionary search are also presented. Trained on 20000 unconstrained cursive words from 59 writers and using a 25000 word dictionary the authors reached a 89% character and 80% word recognition rate on test data from a disjoint set of writers. >

Recognition of handwritten cursive Arabic characters

Abstract: An automatic off-line character recognition system for handwritten cursive Arabic characters is presented. A robust noise-independent algorithm is developed that yields skeletons that reflect the structural relationships of the character components. The character skeleton is converted to a tree structure suitable for recognition. A set of fuzzy constrained character graph models (FCCGM's), which tolerate large variability in writing, is designed. These models are graphs, with fuzzily labeled arcs used as prototypes for the characters. A set of rules is applied in sequence to match a character tree to an FCCGM. Arabic handwritings of four writers were used in the learning and testing stages. The system proved to be powerful in tolerance to variable writing, speed, and recognition rate. >

On-line cursive handwriting recognition using speech recognition methods

Abstract: A hidden Markov model (HMM) based continuous speech recognition system is applied to on-line cursive handwriting recognition. The base system is unmodified except for using handwriting feature vectors instead of speech. Due to inherent properties of HMMs, segmentation of the handwritten script sentences is unnecessary. A 1.1% word error rate is achieved for a 3050 word lexicon, 52 character, writer-dependent task and 3%-5% word error rates are obtained for six different writers in a 25,595 word lexicon, 86 character, writer-dependent task. Similarities and differences between the continuous speech and on-line cursive handwriting recognition tasks are explored; the handwriting database collected over the past year is described; and specific implementation details of the handwriting system are discussed. >

Handwritting input apparatus for handwritting recognition using more than one sensing technique

Abstract: Handwriting recognition apparatus including handwriting input apparatus employing at least two different sensing techniques to sense handwriting and symbol identification apparatus receiving an output of the handwriting input apparatus for providing an output indication of symbols represented by the handwriting.

Combined Dictionary Based and Likely Character String Method of Handwriting Recognition

Abstract: In an handwriting recognition process, a list of candidate recognized words is identified (202) as a function of both comparison of dictionary entries to various combinations of recognized character combinations, and through a most likely character string analysis as developed without reference to the dictionary. The process selects (301) a word from the list and presents (302) this word to the user. The user then has the option of displaying (303) this list. When displaying the list, candidate words developed with reference to the dictionary are displayed in segregated manner from the most likely character string word and the most likely string of digits. The user can change the selected word by choosing from the list, or edit the selected word. When the user selects the most likely character string as the correct representation of the handwritten input to be recognized, the process automatically updates (310) the dictionary to include the most likely character string. The same process can occur when the user selects the most likely string of digits.

Word-level training of a handwritten word recognizer based on convolutional neural networks

Abstract: We introduce a new approach for online recognition of handwritten words written in unconstrained mixed style. Words are represented by low resolution "annotated images" where each pixel contains information about trajectory direction and curvature. The recognizer is a convolutional network which can be spatially replicated. From the network output, a hidden Markov model produces word scores. The entire system is globally trained to minimize word-level errors.

Analysis and recognition of alphanumeric handprints by parts

Abstract: In this paper, an advanced hierarchical model has been proposed to produce a more effective character recognizer based on the probability of occurrence of the patterns. New definitions such as crucial parts, efficiency ratios, degree of confusion, similar character pairs, etc. are also given to facilitate pattern analysis and character recognition. Using these definitions, computer algorithms have been developed to recognize the characters by parts, including halves, quarters, and sixths. The recognition rates have been analyzed and compared to those obtained from subjective experiments. Based on the results of both computer and human experiments, a detailed analysis of the crucial parts and the Canadian standard alphanumeric character set has been made which revealed some fundamental characteristics of these handprint models. The results should be useful to pattern analysis and recognition, character understanding, handwriting education, and human-computer communication. >

Methods and systems for performing handwriting recognition from raw graphical image data

Abstract: Methods and systems for performing handwriting recognition which include, in part, application of stochastic modeling techniques in conjunction with language modeling. Handwriting recognition is performed on a received data set, which is representative of a handwriting sample comprised of one or more symbols. Recognition is performed by representing the data set as a sequence of features and then processing the features utilizing stochastic modeling in conjunction with an evolutional grammer for performing stroke identification, to identify the handwriting sample.

Fundamentals in handwriting recognition

Abstract: 1: Introduction and overview of field.- Frontiers in handwriting recognition.- 2: Handwritten character recognition.- Historical review of theory and practice of handwritten character recognition.- Automatic recognition of handwritten characters.- Learning, representation, understanding and recognition of characters and words - an intelligent approach.- Digital transforms in handwriting recognition.- Pattern recognition with optimal margin classifiers.- 3: Handwritten word recognition.- On the robustness of recognition of degraded line images.- Invariant handwriting features useful in cursive script recognition.- Off-line recognition of bad quality handwritten words using prototypes.- Handwriting recognition by statistical methods.- Towards a visual recognition of cursive script.- A hierarchical handwritten word segmentation.- 4: Contextual methods in handwriting recognition.- Cursive words recognition: methods and strategies.- Hidden Markov models in handwriting recognition.- Language-level syntactic and semantic constraints applied to visual word recognition.- Verification of handwritten British postcodes using address features.- Improvement of OCR by language model.- An approximate string matching method for handwriting recognition post-processing using a dictionary.- 5: Neural networks in handwriting recognition.- Neural-net computing for machine recognition of handwritten English language text.- Cooperation of feedforward neural networks for handwritten digit recognition.- Normalisation and preprocessing for a recurrent network off-line handwriting recognition system.- 6: Architectures for handwriting.- Architectures for handwriting recognition.- 7: Databases for handwriting recognition.- Large database organization for document images.- 8: Signature recognition and verification.- A model-based dynamic signature verification system.- Algorithms for signature verification.- Handwritten signature verification: a global approach.- 9: Application of handwriting recognition.- Total approach for practical character recognition system development.- A pen-based music editor.

Information processing apparatus and control method thereof having user character recognition

Abstract: A hand-held computer with an input pen capable of handwriting recognition. Characters are inputted by a user's manual operation with the input pen on a transparent coordinate input plate in front of a display screen. The computer discriminates pen-input characteristic of the user, and selects a character-recognition dictionary based on the discrimination result.

A system and method for automatic handwriting recognition with a writer-independent chirographic label alphabet

Abstract: 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.

Method and apparatus for recognizing handwriting of different users of a pen-based computer system

Abstract: A computer system and method capable of handwriting recognition and user identification are presented. The computer system includes a CPU, a dual-function display assembly and a stylus. The dual-function display assembly senses the relative position of the stylus with respect to the dual-function display. When an appropriate prompt is displayed, a user responds by application of the stylus to the dual-function display to enter user identity, handwriting, handwriting style, handwriting preferences, and other input to the computer system. Using user-specific handwriting preferences and data, improved handwriting recognition for the user is enabled.

Cursive Word Recognition: Methods and Strategies

Abstract: Although researchers have been working on the field of cursive script recognition (CSR) for more than thirty years, existing systems are still limited to restricted applications and this field of research remains quite open. This paper aims to present the basic principles of the techniques used so far and to classify them according to the type of strategy they are based on. It will mainly focus on off-line recognition although most of the strategies presented here are also valid for on-line recognition.

A method of combining multiple classifiers-a neural network approach

Abstract: Due to different writing styles and various kinds of noise, the recognition of handwritten numerals is an extremely complicated problem. A new trend to tackle this task by the use of multiple classifiers has emerged, which is called "combination of multiple classifiers" (CME). In this paper, a novel approach for CME is developed and discussed in detail. It contains two steps: data transformation and data classification. In data transformation, the output values of each classifier are first transformed into a form of likeness measurement. In data classification, neural-networks have been found very suitable to aggregate the transformed output and produce the final classification decisions. Experiments on 46,451 handwritten numerals have shown a great improvement in recognition by using the present method.

Algorithms for Signature Verification

Abstract: The need to assure that only the right people are authorized to high-security accesses has led to develop systems for automatic personal verification.

A connectionist recognizer for on-line cursive handwriting recognition

Abstract: Shows how the multi-state time delay neural network (MS-TDNN), which is already used successfully in continuous speech recognition tasks, can be applied both to online single character and cursive (continuous) handwriting recognition. The MS-TDNN integrates the high accuracy single character recognition capabilities of a TDNN with a non-linear time alignment procedure (dynamic time warping algorithm) for finding stroke and character boundaries in isolated, handwritten characters and words. In this approach each character is modelled by up to 3 different states and words are represented as a sequence of these characters. The authors describe the basic MS-TDNN architecture and the input features used in the paper, and present results (up to 97.7% word recognition rate) both on writer dependent/independent, single character recognition tasks and writer dependent, cursive handwriting tasks with varying vocabulary sizes up to 20000 words. >

Method and apparatus for arc segmentation in handwriting recognition

Abstract: According to principles of the invention, a method and apparatus are provided that organizes sample text into a format that facilitates character recognition. Sample text is analyzed for those features that define characters. Features that represent useful data for character recognition are stored and analyzed but features not useful for character recognition can be discarded. The sample text is segmented into arcs at each Y-extrema. A center of gravity is calculated for each arc. The arc features are saved as descriptive of the sample text for use in character recognition.

Identification and authentification of handwritten signatures with a connectionist approach

Abstract: TCSF/LER has developed an automatic system to identify or verify off-line handwritten signatures, using a connectionist approach. The authors' method combines image processing which consists in extracting significant parameters from the signature image and classification by a multilayer perceptron which uses the previous parameters as input. In this paper, the image processing step is described according to the intrinsic features of handwriting. Then, the proposed neural networks are compared with others classifiers including pseudo-inverse, k-nearest-neighbours and k-means and the influence of pre-processing and bad segmentation is measured. On a base of around fifty signers (comprising English, French signatures and paraphes), many experimental results are given for identification and verification purposes. >

A new set of moment invariants for handwritten numeral recognition

Abstract: In this paper, a new set of aspect invariant moments for handwritten numeral recognition are presented. These new moments exhibit two useful properties. Firstly, they are aspect invariant. This eliminates the need for size normalization of the unconstrained numerals. Secondly, their dynamic range remains constant with moment order. This overcomes the problem of diminishing high order moments, which occurs when other moment invariants are used. Thus, aspect invariant moments are particularly suitable for use with neural networks. Experimental results (using a multilayer perceptron and the backpropagation learning rule) show that a very high recognition rate (98.73%) and low substitution rate (1.06%) can be achieved on a totally unconstrained handwritten numeral database. >

A fast statistical mixture algorithm for on-line handwriting recognition

Abstract: The automatic recognition of online handwriting is considered from an information theoretic viewpoint. Emphasis is placed on the recognition of unconstrained handwriting, a general combination of cursively written word fragments and discretely written characters. Existing recognition algorithms, such as elastic matching, are severely challenged by the variability inherent in unconstrained handwriting. This motivates the development of a probabilistic framework suitable for the derivation of a fast statistical mixture algorithm. This algorithm exhibits about the same degree of complexity as elastic matching, while being more flexible and potentially more robust. The approach relies on a novel front-end processor that, unlike conventional character or stroke-based processing, articulates around a small elementary unit of handwriting called a frame. The algorithm is based on (1) producing feature vectors representing each frame in one (or several) feature spaces, (2) Gaussian K-means clustering in these spaces, and (3) mixture modeling, taking into account the contributions of all relevant clusters in each space. The approach is illustrated by a simple task involving an 81-character alphabet. Both writer-dependent and writer-independent recognition results are found to be competitive with their elastic matching counterparts. >

Combining bitmaps with dynamic writing information for on-line handwriting recognition

Abstract: Writer independent, large vocabulary online handwriting recognition systems require robust input representations, which make optimal use of the dynamic writing information, i.e. the temporal ordering of the sampled data points. In this paper we describe an input representation for cursive handwriting, which combines this dynamic writing information with static bitmaps used in optical character recognition. This input representation is used with a connectionist recognizer, which is well suited for handling temporal sequences of patterns as provided by this kind of input representation. Our system has been tested on different cursive handwriting recognition tasks with vocabulary sizes up to 20000 words. We achieve recognition rates up to 99.5% on writer independent, single character recognition tasks and up to 98.1% on writer dependent, cursive handwriting tasks.

Handwriting recognition system simultaneously considering shape and context information

Abstract: The speed and accuracy of a computer implemented handwriting recognition system is enhanced by several innovations, including integrated segmentation and context processing. The recognition processing occurs while the user is providing ink data. The system quickly reaches the recognition result once all of the input is received. More than one result may be returned by the system.

Size normalization in on-line unconstrained handwriting recognition

Abstract: In an on-line handwriting recognition system, the motion of the tip of the stylus (pen) is sampled at equal time intervals using a digitizer tablet and the sampled points are passed to a computer which performs the handwriting recognition. In most cases, the basic recognition algorithm performs best for a nominal size of writing as well as a standard orientation (normally horizontal) and a nominal slant (normally fully upright). We discuss and provide solutions to these normalization problems in the context of on-line handwriting recognition. Most of the results presented are also valid for optical character recognition (OCR). Error rate reductions of 54.3% and 35.8% were obtained for the writer-dependent and writer-independent samples through using the proposed normalization scheme. >

Hidden Markov Models in Handwriting Recognition

Abstract: Hidden Markov Models (HMM) have now became the prevalent paradigm in automatic speech recognition. Only recently, several researchers in off-line handwriting recognition have tried to transpose the HMM technology to their field after realizing that word images could be assimilated to sequences of observations. HMM’s form a family of tools for modelling sequential processes in a statistical and generative manner. Their reputation is due to the results attained in speech recognition which derive mostly from the existence of automatic training techniques and the advantages of the probabilistic framework. This article first reviews the basic concepts of HMM’s. The second part is devoted to illustrative applications in the field of off- line handwriting recognition. We describe four different applications of HMM’s in various contexts and review some of the other approaches.

Silent training by error correction for on-line handwritting recognition systems

Abstract: A method for using information provided during error correction for modifying character prototypes in an on-line handwriting recognition system is disclosed. The method allows a user to correct misrecognized handwritten characters by overwriting directly on the displayed ASCII representation of the recognition result for a given character. The rewritten character is then used to silently retrain the system so as to adapt it to the user's particular handwriting style.