Showing papers on "Handwriting recognition published in 1991"

Stylus user interfaces for manipulating text

Abstract: This paper is concerned with pen-based (also called stylus-based) computers. Two of the key questions for such computers are how to interface to handwriting recognition algorithms, and whether there are interfaces that can effectively exploit the differences between a stylus and a keyboard/mouse. We describe prototypes that explore each of these questions. Our text entry tool is designed around the idea that handwriting recognition algorithms will always be error prone, and has a different flavor from existing systems. Our prototype editor goes beyond the usual gesture editors used with styli and is based on the idea of leaving the markups visible.

Understanding handwritten text in a structured environment: determining zip codes from addresses

Abstract: Understanding a block of handwritten text means mapping it into a semantic representation. We describe an approach to reading a block of handwritten text when there are certain loose constraints placed on the spatial layout and syntax of the text. Early recognition of primitives guides the location of syntactic components. A system to read handwritten postal addresses is described as an instance. The semantic representation in this case is a digit string (ZIP Code). Methods for segmenting a string of digits into components and for recognizing digits using a multiplicity of recognizers are given.

On-line handwriting recognition using a prototype confusability dialog

Abstract: A handwriting recognition system in which a user, on-line can reduce similarity between different prototypes. The user interactively can delete a prototype or add a new prototype, while at the same time is not allowed to delete a prototype when it is the only prototype for a given character.

On-line run-on character recognizer: design and performance

Abstract: A recognize-then-segment recognizer of unconstrained handprinting uses a unified tablet-display to provide a paper-like computer interface. Whereas most handwriting recognition systems segment and then recognize, this one recognizes and then finds the best segmentation. It classifies strokes, generates character hypotheses, and verifies hypotheses to estimate the optimal character sequence for each word of run-on handwritten characters. Linguistic constraints can limit the choices. The system is implemented on an IBM workstation, accepts run-on characters written on a tablet, and performs recognition in real time.

Recognition of handwritten Katakana in a frame using moment invariants based on neural network

Abstract: A method of pattern recognition using a three-layered feedforward neural network is described. Experiments were carried out for handwritten katakana in a frame recognition using the neural network. The problem of scale and translation recognition of handwritten characters using the neural network is described, and the relation of the recognition data set to the recognition rate is examined. The normalization of images using moment invariants is examined. First, translation normalization is achieved by translating the origin to the center of gravity of an image. Secondly, scale normalization is executed. Experiments were carried out in which the number of recognition categories was 5, 10, 20, and 46. Furthermore, experiments were carried out where the sets of recognition categories are changed using the Euclidean distance among them. Recognition rate was increased by using this normalization. >

Design and implementation of a dedicated neural network for handwritten digit recognition

Abstract: The automatic recognition of handwritten digits seems to be one of the most promising fields for applications of artificial neural networks; various studies have shown that good recognition rates can be obtained on large 'real-world' data bases. This paper presents: (i) the design of a network architecture, resulting from a stepwise procedure developed at ESPCI for simultaneously building and training a neural network, intended for the automatic recognition of isolated handwritten digits and (ii) a silicon implementation of that network, using a general-purpose neural circuit architecture developed at CSI. >

Handwriting recognition in the GO operating system

Abstract: PenPoint, a new operating system designed and built from the ground up for the unique requirements of mobile, pen-based computers, is described. It is a 32-b, object-oriented, multitasking operating system that is compact and scalable across a wide range of highly portable, pen-based computers. Users control PenPoint computers with special pens that are sensed by the screen. The user writes directly on the screen, combining the convenience of a notebook with the power of a computer. PenPoint translates data entered by handwriting into ASCII. Commands are issued by pointing and by gestures such as circling and scratch out. >

An Evaluation of Recogniton Accuracy for Discrete and Run-On Writing

Abstract: In an effort to reach markets in which a keyboard/mouse interface is difficult or inconvenient to use, manufacturers are now beginning to introduce light-weight portable computers which recognize hand-printed characters. The recognition accuracy that these new computers are able to achieve will be a critical factor in determining their acceptance by users. There are, however, few published studies of handwriting recognition accuracy and the variables which affect accuracy. The purpose of this study was to assess recognition accuracy as a function of a number of factors which might vary in the real-world use of handwriting recognition systems. These factors included style of writing, amount of training, interval of disuse, and alphabet. The findings suggested that recognition accuracy reached a steady-state level with a relatively small amount of training and remained at that level for as long as a month (the longest interval tested in this study). For an 82-character alphabet, character recognition accura...

A new self-organizing method and its application to handwritten digit recognition

Abstract: A self-organizing method for neural networks is proposed. This method reduces the calculation for learning considerably, and can be applied to real application problems, where many samples must be treated. The method has been applied to handwritten digit recognition. Samples incorrectly recognized have been reduced to 1/4 (learning data) or 2/3 (unknown data), compared with the multiple similarity method, which is a conventional statistical pattern classification method. >

Audio-augmented handwriting recognition

Abstract: An improved data-entry apparatus for entering handwritten data is disclosed. The user enters a word (or portion thereof, depending on the language and notation used) into a touchpad and speaks the word. Features are extracted from the spoken information. The touchpad data are indicative of any of a number of candidate words, and a multiplicity of speech portion templates are generated, each template indicative of one of the candidate words. The apparatus evaluates the correlation between the extracted features and the features of each generated speech portion template, and the speech portion template having the highest correlation with the extracted features determines the recognized word. Optionally a speech synthesizer speaks the word and an opportunity is provided so the user may confirm the correctness of the recognition.

Computer algorithms for recognizing the distinct parts of handprinted characters

Abstract: The authors studied several computer algorithms by evaluating the recognition rates on distinct parts of handprinted characters. A regional decomposition method is to facilitate pattern analysis and recognition, by which a complicated pattern can be split into simpler parts or subpatterns. A hierarchy model is also proposed to identify the attributes in different hierarchic levels of patterns so that the recognition rates of the different parts can be calculated by a simplified, uniform, computational scheme. The computed results coincide with those of subjective experiments, but they are more precise and complete. The total mean score of recognition rates of parts obtained from the proposed algorithms was 30% higher than that from human experiments. >

AI Approach to Hand Written Devnagiri Script Recognition

Abstract: In this paper, a system for recognizing hand written Indian Devnagiri script has been proposed. This system uses an AI approach to integrate information from diverse sources. It has three levels of abstraction low, medium and high. At each level of abstraction, knowledge appropriate to that level is used to identfy the components of the higher level concept. At low level of abstraction, a given document is segmented into components, at the meduim level features are extracted from the segment, and at the high level segments are reconized with available contextual the help of information. To deal with imprecise information a new approach based on the fuzzy logic concept has been suggested.

Method of discriminating handwritten character

Abstract: PURPOSE: To improve the accuracy and speed of a situation identification method by discriminating a first character from a second character provided with similar characteristics. CONSTITUTION: An identification measure relating to the first character and the second character is decided by a step for evaluating the respective plural prototype first and second characters along with a latent identification measure during the session of training. Then, along with the identification measure decided beforehand, an input character identified as either one of the first prototype character or the second prototype character is analyzed during a handwriting recognition session. The step for performing evaluation is provided with the step for calculating an excellent value relating to the first and second prototype characters.