Omron Tateisi Electronics Co.

Research Development Corporation of Japan

Mitsui High-tec Incorporated

K. Ushiku & Co.

Takeshi Yamakawa

Tsutomu Ishida

Fumio Ueno

Yuji Shirai

Toyoshi Odahara

Naohiro Inagawa

The invention aims at recognition of a handwritten input character on-line with quite high accuracy. The method of on-line handwritten input character recognition of the invention is characterized in that ordinary strokes and transition strokes and/or start-end (s-e) strokes of a handwritten input character sampled on-line are compared with ordinary strokes and transition strokes and/or s-e strokes of dictionary's characters previously registered in a dictionary and the character corresponding to the handwritten input character is recognized on the basis of the result of the comparison. Otherwise, when the dictionary's character most similar to the input character corresponds to a preset character, the handwritten input character is identified by using characteristic features of the corresponding character. Thus, by comparing ordinary strokes and transition strokes and/or s-e strokes of a handwritten input character sampled on-line with ordinary strokes and transition strokes and/or s-e strokes of dictionary's characters previously registered in a dictionary and recognizing the character corresponding to the handwritten input character on the basis of the result of the comparison, a handwritten input character which was difficult to recognize only by means of ordinary strokes can be recognized with high accuracy.

Method and apparatus for on-line handwritten input character recognition

Applicable rules (IF-THEN rules) are generated with use of predetermined membership functions concerning input and output variables in response to entry of input and output values. Accordingly, time and labor required to make rules can be simplified. In addition, it can be also verified, by making fuzzy inferences according to the generated rules, whether or not the rules are appropriate.

Rule generating and verifying apparatus for fuzzy control using

A programmable multi-membership function circuit comprises at least one or preferably two Z function circuits, at least one or preferably two S function circuits, and a fuzzy logic circuit for calculating fuzzy logic from the output of the Z function circuits and the output of the S function circuits. The fuzzy logic circuit comprises a MIN (intersection) circuit and a MAX (union) circuit, or the combination of these circuits.

Fuzzy membership function circuit

A fuzzy computer which carries out fuzzy operations using membership functions. This fuzzy computer readily processes implications made up of an antecedent expressed by fuzzy values and a consequent expressed by singleton values. This fuzzy computer includes a fuzzy processor, fuzzy controller and a MAX circuit block composite device used in same, and in addition, it contains grade-controllable membership function circuits, grade-controllable membership function generator circuits and center of gravity determination circuits which function as a useful circuit called a defuzzifier for converting fuzzy quantities to definitive values.

Fuzzy computer

Applicable rules (IF-THEN rules) are generated with use of predetermined membership functions concerning input and values. Whether the rules are appropriate is verified by making fuzzy inferences according to the generated rules with at least one of the rules temporarily excluded.

Rule generating and verifying apparatus for fuzzy control

A multivalued Arithmetic Logic Unit (ALU) is composed of a multivalued signal source, a memory array, a selection array, an AND array and an output circuit. The multivalued signal source generates signals each of which represents a logic value of multivalued logic. The memory array is provided with an address line group for each and every function to be inplemented, each address line group comprising a number of address lines. Which multivalued logic signals will appear on the address lines of each address line group depends upon a program based on the truth table of the corresponding function. Any one of the plural address line groups is selected by the selection array, to which a signal designating the function to be implemented is applied. One address line in the selected address line group is selected by the AND array, which has an input signal applied thereto, and the logic value signal on the selected line is delivered via the output circuit.

Multivalued ALU

Disclosed are basic circuits operable in a current mode in multivalued logic circuit systems, analog circuit systems and the like. Examples of the basic circuits are a successor, quantizer, adder, subtractor, divider, multiplier, decoder, literal circuit, equivalence circuit, bilateral T-gate, complement literal circuit and h operator circuit. These basic circuits are realized by using floating threshold switching circuits, floating window switching circuits, threshold SPDT switching circuits, and the like.

Basic circuitry particularly for construction of multivalued logic

A multivalued ALU is composed of a multivalued signal source, a memory array, a selection array, an AND array and an output circuit. The multivalued signal source generates signals each of which represents a logic value of multivalued logic. The memory array is provided with an address line group for each and every function to be implemented, each address line group comprising a number of address lines. Which multivalued logic signals will appear on the address lines of each address line group depends upon a program based on the truth table of the corresponding function. Any one of the plural address line groups is selected by the selection array, to which a signal designating the function to be implemented is applied. One address line in the selected address line group is selected by the AND array, which has an input signal applied thereto, and the logic value signal on the selected line is delivered via the output circuit.

A fuzzy computer basically includes a plurality of fuzzy membership function generator circuits, and a fuzzy inference engine for executing a predetermined fuzzy operation among fuzzy membership functions that have been generated. A fuzzy membership function is represented by electric signals distributed on a plurality of lines.

Fuzzy logic computers and circuits

A fuzzy logic circuit comprising a current mirror comprising an FET, a first input current source connected to the input side of the current mirror, a second input current source, a wired OR connected at its input side to the output side of the current mirror and to the second input current source, and an output terminal connected to the output side of the wired OR.

Fuzzy logic semifinished integrated circuit

Disclosed are basic circuits operable in a current mode in multivalued logic circuit systems, analog circuit systems and the like. Examples of the basic circuits are a successor, quantizer, adder, substracter, divider, multiplier, decoder, literal circuit, equivalence circuit, bilateral T-gate, complement literal circuit and h operator circuit. These basic circuits are realized by using floating threshold switching circuits, floating window switching circuits, threshold SPDT switching circuits, and the like.

Growing community of inventors

Iizuka, Japan

Takeshi Yamakawa