EP0122543A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Method of image processing
Assignee: General Electric Co
•
Filing: 1984-04-05
•
Granted: —
•
Expires: 2004-04-05
Abstract
Abstract A method for determining the average gray value of a plurality of regions within a digitized electronic video image and for determining the color of the region from the average gray value. Initial image segmentation is accomplished by thresholding a multibit digital value into a one bit black and white representation of a picture element of the region. The gray values of the picture elements within either a black or a white region can then be analysed to determine the average gray value by constructing a histogram of each region and eliminating from the histogram the picture elements not associated with the actual color or shading of the region of interest. The remaining picture elements are averaged to obtain the average gray value for the region.
Inventors
- 👤 George Frazer Blackwell
- 👤 Harold Woodruff Tomlinson, Jr.
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-08 16:35
CPC Classifications
B; B07; B07C; B07C5/00; B07C5/34; B07C5/342; B07C5/3422; G; G06; G06T; G06T7/00; G06T7/90; G06V; G06V10/00; G06V10/20; G06V10/28; G06V20/00; G06V20/60; G06V20/66; G06T2207/00; G06T2207/10; G06T2207/10024
Claims Analysis
Total Claims: 8
Claim 1
Independent Claim
163 words
A visual image processing method for digitally processing an electronic monochrome video image of an object within a predefined field of view so as to automatically identify the color of the object, said method comprising the steps of: converting a predetermined visual field of view to a sequence of digital electronic video signals each of which represents the gray scale intensity of a corresponding elemental picture element of a two dimensional view of such a visual field of view; constructing a histogram of the frequency of occurrency of the gray scale intensity values over the field of view; eliminating from the histoqram gray scale values not associated with reflections attributable to the color of the object; computing an average gray scale value for the object as a function of the remaining gray scale values in the histogram; and comparing the averaqe gray scale value for the object to predetermined gray scale values for known colors to thereby identify the color of the object.
Claim 2
Dependent Claim
163 words
A visual image processing method for digitally processing an electronic monochrome video image of an object within a predefined field of view so as to automatically identify the color of the object, said method comprising the steps of: converting a predetermined visual field of view to a sequence of digital electronic video signals each of which represents the gray scale intensity of a corresponding elemental picture element of a two dimensional view of such a visual field of view; constructing a histogram of the frequency of occurrency of the gray scale intensity values over the field of view; eliminating from the histoqram gray scale values not associated with reflections attributable to the color of the object; computing an average gray scale value for the object as a function of the remaining gray scale values in the histogram; and comparing the averaqe gray scale value for the object to predetermined gray scale values for known colors to thereby identify the color of the object.
Claim 3
Dependent Claim
54 words
The method of Claim 1 wherein the step of eliminating gray scale values from the histogram comprises the steps of: establishing empirically a percent of picture elements within the field of view required to identify the object color; and disregarding any gray scale values associated with less than a predetermined number of picture elements.
Claim 4
Dependent Claim
29 words
The method of Claim 1 wherein each of the gray scale intensity values are thresholded against a predetermined threshold level to identify those picture elements associated with the object.
Claim 5
Dependent Claim
39 words
The method of Claim 3 wherein the thresholding step comprises converting at least one bit of the digital electronic signal to a threshold bit indicative of the presence of the object within the picture element corresponding to the signal.
Claim 6
Dependent Claim
76 words
The method of Claim 1 and including the additional steps of: identifying the possible colors to be associated with the object; constructing a graph of the relative reflectivity of each color for the object as a function of the frequency of incident light: selecting a light frequency which provides distinct gray scale values for each color object to be identified; and obtaining the monochromatic video image through a light filter corresponding to the selected light frequency.
Claim 7
Dependent Claim
128 words
The method of Claim 1 wherein the steps of converting the predetermined field of view to a sequence of digital electronic video signals comprises the additional steps of: computing the gray scale values for a plurality of predetermined windows within the field of view; summing the computed gray scale values to obtain an average normalization factor for the field of view; comparing the average normalization factor to a similarly obtained normalization factor for each subsequently examined field of view; dividing any difference in the respective normalization factors by the number of windows in the field of view to obtain a correction factor; and combining the correction factor with the average gray scale value for each window to thereby adjust the gray scale intensity values for overall light variation.
Claim 8
Dependent Claim
76 words
The method of Claim 1 wherein the step of converting the predetermined field of view to a sequence of digital electronic video signals comprises the additional steps of: computing the average gray scale value for each of a plurality of windows within the field of view; and subtracting the computed average gray scale value of each window from the corresponding gray scale intensity value for that window to thereby obtain a normalized gray scale intensity value.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.