EP0054842A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Figure recognizing system
Assignee: Toshiba Corp
•
Filing: 1981-12-09
•
Granted: —
•
Expires: 2001-12-09
Abstract
Abstract In a figure recognizing system according to the invention comprising a scanning section (3), a detecting section (5), thesauruses (9, 11), a similarity computing section (7), a storage register (23) for storing detected information from the detecting section (5) and a recognizing section (21) for recognizing the final letter information, threshold table means (15) in which letter combinations and corresponding threshold levels are stored as pairs, a category judgement section (13) for receiving the output of the similarity computing section (7), obtaining a similarity difference from the maximum and next maximum similarity values and comparing the similarity difference thus obtained and a corresponding threshold level in the threshold table means (15) to judge the category of said letter, format table means (19) where a predetermined category series is stored, and format judging means (17) for comparing the category supplied from the detecting section (5) and category judgement section (13) connected thereto and the category series supplied from the format table means (19).
Inventors
- 👤 Masaaki Shizuno
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-10-26 22:00
CPC Classifications
G; G06; G06F; G06F18/00; G06F18/20; G06F18/25; G06F18/254
Claims Analysis
Total Claims: 4
Claim 1
Independent Claim
286 words
A figure recognizing system comprising a scanning section (3) for reading out letter information of various letter species recorded on a recording'medium, a detecting section (5) connected to said scanning section (3) for effecting letter detection from the letter information from said scanning section (3), thesauruses (9, 11) consisting of standard letter patterns of various letter species corresponding to said various letter species, a similarity computing section (7) for receiving letter information from said detecting section (5) and standard letter pattern information from said thesauruses (9, 11) and computing the similarity corresponding to the letter information from said detecting section (3), storage means (23) for storing the detected information from said detecting section (5), and a recognizing section (21) connected to said storage means (23) and similarity computing section (7) for recognizing the content of said storage means (23) according to the similarity from said similarity computing section (7) and providing final letter information, charac- . terized in that there are provided (a) threshold table means (15) in which letter combinations and threshold levels for the respective letter combinations are stored as pairs; (b) a category judgement section (13) for re- ceiving the output of said similarity computing section (7), obtaining a similarity difference from the maximum and next maximum of said similarity and comparing said similarity difference and a corresponding threshold level of said threshold table means (15) to judge the category of said letter; (c) format table means (19) where a predetermined category series is stored; and (d) format judgement means (17) connected to said detecting section (5) and category judgement section (13) for comparing the category supplied from said detecting section (5) and a category series supplied from said format table means (19).
Claim 2
Dependent Claim
286 words
A figure recognizing system comprising a scanning section (3) for reading out letter information of various letter species recorded on a recording'medium, a detecting section (5) connected to said scanning section (3) for effecting letter detection from the letter information from said scanning section (3), thesauruses (9, 11) consisting of standard letter patterns of various letter species corresponding to said various letter species, a similarity computing section (7) for receiving letter information from said detecting section (5) and standard letter pattern information from said thesauruses (9, 11) and computing the similarity corresponding to the letter information from said detecting section (3), storage means (23) for storing the detected information from said detecting section (5), and a recognizing section (21) connected to said storage means (23) and similarity computing section (7) for recognizing the content of said storage means (23) according to the similarity from said similarity computing section (7) and providing final letter information, charac- . terized in that there are provided (a) threshold table means (15) in which letter combinations and threshold levels for the respective letter combinations are stored as pairs; (b) a category judgement section (13) for re- ceiving the output of said similarity computing section (7), obtaining a similarity difference from the maximum and next maximum of said similarity and comparing said similarity difference and a corresponding threshold level of said threshold table means (15) to judge the category of said letter; (c) format table means (19) where a predetermined category series is stored; and (d) format judgement means (17) connected to said detecting section (5) and category judgement section (13) for comparing the category supplied from said detecting section (5) and a category series supplied from said format table means (19).
Claim 3
Dependent Claim
311 words
The figure recognizing system according to claim 1, characterized in that said category judgement section (13) includes: a first comparing circuit (61) for comparing the similarities provided from said similarity computing section (7) to derive the maximum similarity (S N1 , S Al ) and the letter name (CN l , C A1 ) thereof and compute high and low values (S 1 , S 2 ) of said maximum similarity (S N1 S Al ) and letter names (C l , C 2 ) corresponding to said high and low values (S 1 , S 2 ); a maximum value reserving register (63) for storing the high and low values (S 1 , S 2 ) output from said first comparing circuit (61) and corresponding letter names (C 1 , C 2 ); a subtracting circuit (65) for receiving the output of said maximum value reserving register (63) and subtracting said low value (S 2 ) from said high value (S 1 ); a retreaving circuit (67) for receiving the output of said maximum value reserving register (63) and finding out the letter name combination coincident with said combination of letter names (C 1 , C 2 ) to provide the corresponding threshold level (T H ); a second comparing circuit (71) for receiving the output of said subtracting circuit (65) and the output of said retreaving circuit (67) and comparing said subtracted value (S 1 - S 2 ) and said threshold level (T H ) to provide the category name to which C l belongs if S 1 - S 2 ≧ T H and provide both the category name to which C l belongs and category name to which C 2 belongs if S 1 - S2 < TH; and a category storage memory (73) for storing a category name provided from said second comparing circuit (71).
Claim 4
Dependent Claim
111 words
The figure recognizing system according to claim 1, characterized in that said format judgement section (17) includes: a format selecting circuit (77) for receiving the block position data supplied from said detecting section (5) and selecting only the formats permissible in the block position of the received data as a category series; and a format comparing circuit (75) for comparing the n-th category of the category series supplied from said format selecting circuit (77) and the n-th letter category supplied from said category judgement section (13) and supplying the block and formats to said recognizing section (21) if a coincidence is obtained while discarding the block if no coincidence is obtained.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.