EP0585098A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Sign recognition apparatus and method and sign translation system using same
Assignee: Hitachi Ltd
•
Filing: 1993-08-23
•
Granted: —
•
Expires: 2013-08-23
Abstract
Abstract In continuous sign language recognition, reference sign language patterns of good quality are generated. Continuous sign language patterns and reference sign language patterns are efficiently compressed. The compressed continuous sign language patterns are sequentially and directly matched with the compressed reference sign language patterns to recognize the sign language at high speed and with high precision. A reference sign pattern generating unit (3) generates a reference sign language pattern by normalizing sample patterns while taking into consideration of their nonlinear compression/expansion and by calculating an average of the sample patterns. A continuous sign language recognition unit (5) recognizes a continuous sign language at high speed by sequentially matching the continuous sign language of time sequential patterns with reference sign language patterns while allowing nonlinear expansion and compression in the time domain. A sign language translation system is provided in which a sign language as well as the facial expression or emotion of a sign language user is recognized and converted into a spoken language with emotion, and transferred in the form of texts, voices, sign languages of another type to a particular partner among a plurality of unknown system users.
Inventors
- 👤 Hiroshi Sakou
- 👤 Hirohiko Hitachi Daiyon Kyoshinryo Sagawa
- 👤 Masahiro Abe
- 👤 Akira Ichikawa
- 👤 Kiyoshi Inoue
- 👤 Kiyoshi Arai
- 👤 Takanori Shimura
- 👤 Yuji Toda
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-09 14:21
CPC Classifications
G; G09; G09B; G09B21/00; G09B21/009; G06; G06F; G06F18/00; G06F18/20; G06F18/25; G06F18/254; G06F18/256; G06F40/00; G06F40/40; G06F40/55; G06V; G06V10/00; G06V10/70; G06V10/77; G06V10/80; G06V10/809; G06V10/811; G06V30/00; G06V30/10; G06V30/24; G06V30/248; G06V40/00; G06V40/20; G06V40/28
Claims Analysis
Total Claims: 20
Claim 1
Independent Claim
75 words
A sign language recognition apparatus for recognizing a continuously expressed sign language, comprising: input means (1, 1') for inputting the continuously expressed sign language as a time sequential pattern; means (26) for generating a reference sign language pattern by averaging sample time sequential patterns; means (27) for storing said reference sign language pattern; and means (28) for matching said time sequential pattern with said reference sign language pattern to recognize said continuously expressed sign language.
Claim 2
Dependent Claim
74 words
A sign language recognition apparatus according to Claim 1, wherein said means (26) for generating said reference sign language pattern includes means (261, 262, 263, 264, 265) for obtaining correspondence points between said sample time sequential patterns having a nonlinear expansion/compression in a time axis direction, while nonlinearly moving said sample time sequential patterns in the time axis direction, and obtaining an average of said sample time sequential patterns at each said correspondence point.
Claim 3
Dependent Claim
55 words
A sign language recognition apparatus according to Claim 1, wherein said sign language recognition means (28) includes means (282, 283) for recognizing said continuously expressed sign language by sequentially matching said sign language time sequential pattern with said reference sign language pattern stored in advance while allowing a nonlinear expansion/compression in a time axis direction.
Claim 4
Dependent Claim
73 words
A sign language recognition apparatus according to Claim 3, wherein said sign language recognition means (28) includes means (281) for deriving characteristic points of said sign language time sequential pattern and said reference sign language pattern, and in accordance with said derived characteristic points, compressing said sign language time sequential pattern and said reference sign language patter, wherein said compressed time sequential pattern is directly matched with said compressed reference sign language pattern.
Claim 5
Dependent Claim
89 words
A sign language recognition apparatus according to Claim 4, further comprising means (281, 2661, 2662, 2663, 2664) for compressing a sign language pattern by using, as said characteristic points specific to said sign language time sequential pattern, at least one of a time when the pattern vector velocity becomes minimum, a time when the direction change of the velocity vector exceeds a threshold value, a time then an accumulated value of direction changes of the velocity vector exceeds a threshold value, and a time when an acceleration becomes minimum.
Claim 6
Dependent Claim
50 words
A sign language recognition apparatus according to Claim 5, further comprising means (281, 2665) for compressing said sign language time sequential pattern by using at least ones of pattern vectors at said respective characteristic points, linear approximations of vectors between said characteristic points, and time lengths between said characteristic points.
Claim 7
Dependent Claim
69 words
A recognition apparatus for recognizing a continuous pattern, comprising: input means (1, 1') for inputting a continuously expressed sign language as a time sequential pattern; means (26) for generating a reference sign language pattern by averaging sample time sequential patterns; means (27) for storing said reference sign language pattern; and means (28) for matching said time sequential pattern with said reference sign language pattern to recognize said continuous pattern.
Claim 8
Dependent Claim
84 words
A sign language recognition method of recognizing a continuously expressed sign language, comprising the steps of: inputting sample sign language patterns for generating a reference sign language pattern as first time sequential patterns, and generating said reference sign language pattern by averaging said first time sequential patterns (1301 - 1308); inputting a sign language to be recognized as a second time sequential pattern (1501 - 1503); and matching said reference sign language pattern with said second time sequential pattern to recognize said sign language.
Claim 9
Dependent Claim
97 words
A sign language recognition method according to Claim 8, further comprising the steps of: deriving first characteristic points from said averaged first time sequential pattern, and in accordance with said first characteristic points, compressing said first time sequential pattern to generate said reference sign language pattern (1308, 1401 - 1410); deriving second characteristic points from said second time sequential pattern, and in accordance with said second characteristic points, compressing said second time sequential pattern (1401 - 1410); and matching said compressed reference sign language pattern with said compressed second time sequential pattern to recognize said sign language.
Claim 10
Dependent Claim
160 words
A sign language translation system having input means (1, 1') for inputting a continuously expressed sign language as time sequential data, means (2') for recognizing a sign language from said time sequential data, and means (3) for translating said recognized sign language into a spoken language, said sign language recognition means comprising: a sign language word dictionary (22) for storing first sign language time sequential data of each sign language word; means (21) for calibrating second sign language time sequential data inputted from said input means so as to make said first sign language time sequential data stored in said sign language word dictionary correspond to said first sign language time sequential data; and means (23) for matching said second sign language time sequential data calibrated by said calibration means with said first sign language time sequential data stored in said sign language word dictionary, and recognizing the sign language word corresponding to said second sign language time sequential data.
Claim 11
Dependent Claim
109 words
A sign language translation system according to Claim 10, further comprising: matching means (24) for receiving said second sign language time sequential data of a sign language word and said first sign language time sequential data corresponding to said second sign language time sequential data, obtaining and outputting correspondences between both said sign language sequential data at each timing; and selection means (25) for selecting one of said second sign language time sequential data and an output of said matching means, and outputting said selected one to said calibration means, wherein said calibration means learns recognition parameters for the calibration in accordance with an output of said matching means.
Claim 12
Dependent Claim
24 words
A sign language translation system according to Claim 11, wherein a neural network is further provided for learning said recognition parameters for the calibration.
Claim 13
Dependent Claim
42 words
A sign language translation system according to Claim 10, wherein said spoken language translation means (3) adds a dependent word to the sign language word outputted from said sign language recognition means, in accordance with a rule, and outputting a spoken language.
Claim 14
Dependent Claim
82 words
A sign language translation system according to Claim 10, further comprising means (4) for inputting a portrait of a sign language user, look recognition means (5) for recognizing the look of the portrait to obtain the emotion type and the emotion degree (intensity), and processor means (16) for inputting a spoken language outputted from said spoken language translation means (3) and the emotion type and degree outputted from said look recognition means (5), and outputting a spoken language added with emotional adjectives.
Claim 15
Dependent Claim
35 words
A sign language translation system according to Claim 14, further comprising sound output means (11, 12) for synthesizing and outputting sounds, wherein said processor means (16) outputs sounds corresponding to the emotion type and degree.
Claim 16
Dependent Claim
34 words
A sign language translation system according to Claim 14, further comprising test output means (13) for outputting a text, wherein said processor means (16) outputs said text corresponding to the emotion type and degree.
Claim 17
Dependent Claim
39 words
A sign language translation system according to Claim 14, further comprising sign language graphics means (13, 14) for outputting a sign language as CG, wherein said processor means (16) outputs said CG corresponding to the emotion type and degree.
Claim 18
Dependent Claim
23 words
A sign language translation system according to Claim 14, further comprising voice input means (9, 10) having a microphone and voice recognition means.
Claim 19
Dependent Claim
22 words
A sign language translation system according to Claim 14, further comprising character input means (8) for inputting a character from a keyboard.
Claim 20
Dependent Claim
45 words
A sign language translation system according to Claim 10, wherein said sign language translation system is installed at each of a plurality of stations connected to a local area network so that information can be transferred between a plurality of said sign language translation systems.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.