Showing papers on "Handwriting recognition published in 1989"
TL;DR: Electronic circuits are described which automatically extract these components from the accelerometer output those signal components relevant to the handwriting process and obtain a fully characterized handwriting acceleration signal.
Abstract: Consideration is given to the problem of measuring the acceleration produced by hand-pen movements while one is signing with an accelerometer pen. Acceleration signals are characterized in terms of frequency, phase, and amplitude. This characterization makes possible the extraction from the accelerometer output those signal components relevant to the handwriting process. Electronic circuits are described which automatically extract these components and obtain a fully characterized handwriting acceleration signal. >
57 citations
Patent•
14 Nov 1989
TL;DR: In this paper, a method of handwriting recognition is described, which consists in applying predetermined criterions to a tracing of handwriting or to elements of this tracing, so that several characterizing features of the tracing or of these elements can be determined, comparing characterising features thus determined to those representative of known elements of writing, and identifying one element of the traced tracing with one known element of writing when the comparison of their characterizing feature scores gives a predetermined result.
Abstract: A method of recognition of handwriting consisting in applying predetermined criterions to a tracing of handwriting or to elements of this tracing so that several characterizing features of this tracing or of these elements be determined, comparing characterizing features thus determined to characterizing features representative of known elements of writing and identifying one element of the tracing with one known element of writing when the comparison of their characterizing features gives a predetermined result, wherein the improvement consists in the setting up of a sequence of predetermined operating steps in accordance with predetermined characterizing features by applying criterions to the tracing elements.
23 citations
23 May 1989
TL;DR: The authors present a hierarchical system for character recognition with hidden Markov model knowledge sources that solve both the context sensitivity problem and the character instantiation problem, thus permitting real-time multifont and multisize printed character recognition as well as handwriting recognition.
Abstract: The authors present a hierarchical system for character recognition with hidden Markov model knowledge sources that solve both the context sensitivity problem and the character instantiation problem. The system achieves 97 to 99% accuracy using a two-level architecture and has been implemented using a systolic array, thus permitting real-time (1 ms per character) multifont and multisize printed character recognition as well as handwriting recognition. >
18 citations
01 Oct 1989
TL;DR: Four input devices were compared in a data entry task by speed and accuracy scores, showing the keyboard to be fastest and the cursor keys to be slowest in data entry.
Abstract: Four input devices were compared in a data entry task by speed and accuracy scores. The input devices were: Linus pen (a handwriting recognition system), optical mouse, cursor keys, and alphabetic ...
10 citations
08 May 1989
TL;DR: A hierarchical system for character recognition with hidden-Markov model knowledge sources that solves both the context-sensitive problem and the character-instantiation problem is presented, thus permitting real-time multifont and multisize printed character recognition as well as handwriting recognition.
Abstract: A hierarchical system for character recognition with hidden-Markov model knowledge sources that solves both the context-sensitive problem and the character-instantiation problem is presented. The algorithms and the structure of the system are described, and its operation is discussed. The system achieves 97 to 99% accuracy using a two-level architecture and has been implemented using a systolic array, thus permitting real-time (1 ms per character) multifont and multisize printed character recognition as well as handwriting recognition. >
8 citations
09 Apr 1989
TL;DR: An algorithm for recognizing printed Greek letters that consists of a preprocessor for thinning and noise renewal and a classifier which differentiates each of the characters based on features such as existence of closed curve, number of intersections,Number of free ends, horizontal and vertical symmetry, and existence of diagonal neighbors.
Abstract: The authors have developed and implemented an algorithm for recognizing printed Greek letters. The scheme consists of a preprocessor for thinning and noise renewal and a classifier which differentiates each of the characters based on features such as existence of closed curve, number of intersections, number of free ends, horizontal and vertical symmetry, and existence of diagonal neighbors. An algorithm based on mathematical modeling of the characters to classify the handwritten Greek letters is also investigated. Experimental results indicate that the percentage of successful recognition is almost 100% depending on how well the characters were thinned. >
3 citations
10 Apr 1989
TL;DR: A handwritten machine drawing recognition system has been developed that is based on a knowledge-based vision paradigm and segmentation is tightly related to partial recognition in which a hierarchical projection method is used and each divided region is recognized by the model-based system.
Abstract: A handwritten machine drawing recognition system has been developed that is based on a knowledge-based vision paradigm. The system is divided into four units: presegmentation, segmentation, partial recognition, and recognition. The segmentation is tightly related to partial recognition in which a hierarchical projection method is used and each divided region is recognized by the model-based system. Thus, partially recognized and pending regions are globally recognized. The experimental results were quite good. >
1 citations
1 citations
23 May 1989
TL;DR: Simulation results show that the system greatly outperforms its serial processing version, and can process the information at two levels: global and local.
Abstract: A novel knowledge-based parallel processing system has been designed for recognition of handwritten characters. With five quadtree-linked microprocessors, this system can extract features from the character image in four directions simultaneously. Through repetitive order-giving and information-gathering between the master and the slaves, the system can process the information at two levels: global and local. Simulation results show that the system greatly outperforms its serial processing version. >
08 May 1989
TL;DR: An online computer system has been developed to recognize handwritten Japanese Hiragana characters that enables a user to write naturally on paper while recognition takes place, using a biro pen modified with a rubber membrane and three strain gauges.
Abstract: An online computer system has been developed to recognize handwritten Japanese Hiragana characters. The system requires only detection of pen-up and the velocity of the pen in the two horizontal planes of the paper. No absolute coordinates need be collected. This enables a user to write naturally on paper while recognition takes place, using a biro pen modified with a rubber membrane and three strain gauges. Such tolerance towards the user creates scope for considerable ambiguity, techniques from artificial intelligence, in particular from natural-language processing are used to help with this problem. A grammar is used to describe the target character shapes, and the input stream is classified by parsing. For characters close to the target, the most likely of the hypotheses was correct for over 95% of the characters drawn by three native Japanese. For poorly drawn characters the recognition rate, based upon the most likely hypothesis, drops to around 80%, but the set of hypotheses almost always contains the target character. >
22 Nov 1989
TL;DR: The development of a technique based on unequal weights for topological features extracted from isolated numerals is described, which can be used for recognition of handwritten numerals and compared with existing techniques that propose binary trees for classification.
Abstract: The development of a technique based on unequal weights for topological features extracted from isolated numerals is described. This technique can be used for recognition of handwritten numerals. The technique is compared with existing techniques that propose binary trees for classification. A discussion on additional topological features is also included. These features were found to be useful in some classes of numerals. >