Patent US2642987A successfully refreshed from Google Patents.
US4075604A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method and apparatus for real time image recognition
Assignee: Tasco SpA
•
Filing: 1977-01-25
•
Granted: 1978-02-21
•
Expires: 1997-01-25
Abstract
Abstract Method and apparatus for real time recognition of test images by comparison with sample images. The test image to be recognized is scanned to produce a plurality of analog signals of the luminance levels. These luminance signals are screened to eliminate background signals and are converted to digital signals. A distribution function of the occurrence frequency versus the luminance level is determined from the test image signals. Typical parameters of said distribution function are calculated and compared with sets of stored corresponding parameters derived in a similar manner from known reference sample images. A recognition signal is outputted to indicate the sample image which most closely resembles the test image as determined by said comparison, provided that the quantitatively determined differences between test and sample images are below a predetermined threshold value.
Inventors
- 👤 Mario Marco Degasperi
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-23 13:40
CPC Classifications
G; G06; G06V; G06V10/00; G06V10/20; G06V10/28; G06V10/40; G06V10/42; G06V10/70; G06V10/74; G06V10/75
Claims Analysis
Total Claims: 19
Claim 1
Independent Claim
290 words
A method for real time recognition of a test image supported on a background by comparison with known sample images, and selection of the sample image showing the least difference, comprising the steps of: (a) preparing and storing for reference a plurality of sets of sample typical parameters, each set of typical parameters derived from the luminance of an individual known sample image; (b) reading said test image on said background with a scanning device to produce a plurality of test signals proportional to the levels of luminance of said test image and said background; (c) separating said test signals into discrete accumulations of signals having the same luminance level; (d) eliminating from said plurality of test signals those signals produced from reading of said background; (e) preparing from said separated test image signals a distribution function having luminance levels for one axis and frequency of occurrence of test image signals for the other axis, background signals being absent from said distribution function; (f) operating on said distribution function of said test image signals to determine a set of test image typical parameters from said distribution function; (g) comparing said test image typical parameters with said plurality of sets of sample image typical parameters, each set being compared in sequence, said sets of sample image typical parameters having been prepared in the manner of steps (b) to (f); (h) selecting the one set of sample image typical parameters which in said comparison indicates the least difference with said set of test image typical parameters; (i) comparing said least difference with a threshold value of difference; and (j) generating a signal indicating the sample image providing said least difference when said least difference is less than said threshold value of difference.
Claim 2
Independent Claim
290 words
A method for real time recognition of a test image supported on a background by comparison with known sample images, and selection of the sample image showing the least difference, comprising the steps of: (a) preparing and storing for reference a plurality of sets of sample typical parameters, each set of typical parameters derived from the luminance of an individual known sample image; (b) reading said test image on said background with a scanning device to produce a plurality of test signals proportional to the levels of luminance of said test image and said background; (c) separating said test signals into discrete accumulations of signals having the same luminance level; (d) eliminating from said plurality of test signals those signals produced from reading of said background; (e) preparing from said separated test image signals a distribution function having luminance levels for one axis and frequency of occurrence of test image signals for the other axis, background signals being absent from said distribution function; (f) operating on said distribution function of said test image signals to determine a set of test image typical parameters from said distribution function; (g) comparing said test image typical parameters with said plurality of sets of sample image typical parameters, each set being compared in sequence, said sets of sample image typical parameters having been prepared in the manner of steps (b) to (f); (h) selecting the one set of sample image typical parameters which in said comparison indicates the least difference with said set of test image typical parameters; (i) comparing said least difference with a threshold value of difference; and (j) generating a signal indicating the sample image providing said least difference when said least difference is less than said threshold value of difference.
Claim 3
Dependent Claim
37 words
The method of claim 1 wherein said test signals are produced in analog format, and further comprising the additional step to follow step (b) of: converting individually said plurality of analog test signals to corresponding digital signals.
Claim 4
Dependent Claim
22 words
The method of claim 1 wherein in step (e), there is prepared a distribution function, said prepared function being a distribution histogram.
Claim 5
Dependent Claim
123 words
The method of claim 1 wherein said operation (f) on said distribution function includes the further steps of: (1) integrating said luminance level occurrence frequencies of said distribution function with respect to said luminance levels to produce a summation function of signal occurrence versus said luminance levels, the highest value of summed signal occurrences equalling the total, N, of said image test signals absent all background test signals; (2) selecting a set of individual luminance values corresponding to each of a plurality of individual values of summed signal occurrences, said individual values of summed signal occurrences being selected at intervals in a structured format and including the value N, said selected set of luminance values being said set of test image typical parameters.
Claim 6
Dependent Claim
60 words
The method of claim 1, wherein the comparison in sequence of said test image typical parameters with said sets of typical parameters of said sample images includes calculating the difference between corresponding parameters of said test image and each sample image, and calculating the individual sum of the obtained differences for each of said sets of sample image typical parameters.
Claim 7
Dependent Claim
20 words
The method of claim 5, wherein said differences are weighted by multiplying said differences between corresponding parameters by a constant.
Claim 8
Dependent Claim
16 words
The method of claim 5, wherein said differences between parameters are mathematically raised to a power.
Claim 9
Dependent Claim
76 words
The method of claim 1 wherein said test images, when read as test signals, are decomposed into basic chromatic components, and said sets of sample typical parameters are prepared and stored in corresponding chromatic components from known sample images, and said steps (c), (d), (e), (f), (g), (h), (i), and (j) are implemented on the test signals of each chromatic component, and said sample typical parameters of the same chromatic component are used in said comparison.
Claim 10
Independent Claim
286 words
An apparatus for real time recognition of a test image supported on a background by comparison with known sample images, and selection of the sample image showing the least difference, comprising: (a) means for preparing and storing for reference a plurality of sets of sample typical parameters, each set of typical parameters derived from the luminance of an individual known sample image; (b) scanning means for reading the said test image on said background to produce a plurality of test signals proportional to the levels of luminance of said test image and said background; (c) means for separating said test signals into discrete accumulations of signals having the same luminance level; (d) means for eliminating from said plurality of test signals those signals produced from reading of said background; (e) means for preparing from said separated test image signals a distribution function having luminance levels for one axis and frequency of occurrence of test image signals for the other axis; background signals being absent from said distribution function; (f) means for operating on said distribution function of said test image signals to determine a set of test image typical parameters from said distribution function; (g) means for comparing said test image typical parameters with said plurality of sets of sample image typical parameters, each set being compared in sequence; (h) means for selecting the one set of sample image typical parameters which in said comparison indicates the least difference with said set of test image typical parameters; (i) means for comparing said least difference with a threshold value of difference; and (j) signal generating means for indicating the sample image providing said least difference when said least difference is less than said threshold value of difference.
Claim 11
Independent Claim
286 words
An apparatus for real time recognition of a test image supported on a background by comparison with known sample images, and selection of the sample image showing the least difference, comprising: (a) means for preparing and storing for reference a plurality of sets of sample typical parameters, each set of typical parameters derived from the luminance of an individual known sample image; (b) scanning means for reading the said test image on said background to produce a plurality of test signals proportional to the levels of luminance of said test image and said background; (c) means for separating said test signals into discrete accumulations of signals having the same luminance level; (d) means for eliminating from said plurality of test signals those signals produced from reading of said background; (e) means for preparing from said separated test image signals a distribution function having luminance levels for one axis and frequency of occurrence of test image signals for the other axis; background signals being absent from said distribution function; (f) means for operating on said distribution function of said test image signals to determine a set of test image typical parameters from said distribution function; (g) means for comparing said test image typical parameters with said plurality of sets of sample image typical parameters, each set being compared in sequence; (h) means for selecting the one set of sample image typical parameters which in said comparison indicates the least difference with said set of test image typical parameters; (i) means for comparing said least difference with a threshold value of difference; and (j) signal generating means for indicating the sample image providing said least difference when said least difference is less than said threshold value of difference.
Claim 12
Dependent Claim
77 words
The apparatus of claim 9, wherein said means for separating said test signals into discrete accumulations comprises an address selector circuit for a memory having a capacity equal to a number of preselected luminance levels, each luminance level signal arriving at said address selector driving a corresponding memory cell to transmit its content to an adder where said content is incremented by one unit, said incremented content being then returned through a register to said memory cell.
Claim 13
Dependent Claim
39 words
The apparatus of claim 9, further comprising a counter of the total number of luminance level test signals within two preset end threshold levels of luminance, whereby test signals representative of said background are eliminated from said total number.
Claim 14
Dependent Claim
76 words
The apparatus of claim 9, wherein said means for storing and said means for comparing said sample typical parameters comprise a memory for the typical parameters of sample images, a register for storing the corresponding said typical parameters of the test image to be recognized, said memory and said register being connected to circuit means for providing the differences between said sample and said test parameters and summing the absolute values of said differences thus obtained.
Claim 15
Dependent Claim
18 words
The apparatus of claim 12, further comprising circuit means for weighting the absolute values of said parameter differences.
Claim 16
Dependent Claim
29 words
The apparatus of claim 13, wherein said means for weighting the absolute values of said differences between said parameters includes means to raise said absolute values to a power.
Claim 17
Dependent Claim
23 words
The apparatus of claim 12 wherein said means for comparing said least difference operates on said summed absolute values of said parameter differences.
Claim 18
Dependent Claim
48 words
The apparatus of claim 9, wherein said test image is decomposed by said scanning means into basic chromatic components, said means for separating and accumulating comprising independent storing and accumulating means for each chromatic component of said test image, and said means for separating and accumulating simultaneously operating.
Claim 19
Dependent Claim
64 words
The apparatus, of claim 16 wherein said storing means and said comparing means include a storing and comparing unit for each typical parameter of each basic chromatic component of said test image, and said circuit means for summing said absolute values of said differences are series interconnected, whereby each of said summing circuit means adds to its content the content of the preceding adders.
References Cited (Backward Citations)
US3705383A
Cited
US3805239A
Cited
US3829218A
Cited
US3999047A
Cited
US3858044A
Cited
US3935562A
Cited
US3930230A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1981-02-20 | 1981-08-22 | 1982-02-21 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1985-02-20 | 1985-08-22 | 1986-02-21 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 1989-02-20 | 1989-08-22 | 1990-02-21 | $7700.00 | Window Closed / Lapsed |