US2012076405A1PendingUtilityA1

Automatic detection of calibration charts in images

45
Individually held — no corporate assignee on recordPriority: Jun 8, 2007Filed: Dec 1, 2011Published: Mar 29, 2012
Est. expiryJun 8, 2027(~0.9 yrs left)· nominal 20-yr term from priority
Inventors:Ralph BrunnerDavid Hayward
G06V 30/413G06V 10/242H04N 1/6047
45
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

Methods and apparatuses for locating an embedded color chart in an image are described. In one exemplary method, an image that includes an embedded color chart is located without the intervention of the user. The embedded color chart is verified and used to create a color profile of the image. Furthermore, the orientation angle of the color chart is determined and the image orientation is fixed based on this angle.

Claims

exact text as granted — not AI-modified
1 . A computerized method comprising:
 receiving an image, wherein the image comprises an embedded color chart;   locating the embedded color chart without intervention of a user;   verifying the embedded color chart; and   creating a color profile for the image based on the embedded color chart.   
     
     
         2 . The computerized method of  claim 1 , wherein the locating comprises:
 computing an average horizontal scan line comprising a first set of pulses;   fitting a second set of generated pulses corresponding to a reference color chart to the first set of pulses;   determining if the first set of pulses matches the second set of generated pulses;   computing an average vertical scan line comprising a third set of pulses;   fitting a fourth set of generated pulses corresponding to a reference color chart to the third set of pulses; and   determining if the third set of pulses matches the second set of generated pulses; and   determining the location of the embedded color chart in the image based on the first and third set of pulses.   
     
     
         3 . The computerized method of  claim 2 , wherein said fitting a second set of generated pulses to a first set of pulses comprises matching the number pulses in the second set of generated pulses to the first set of pulses. 
     
     
         4 . The computerized method of  claim 1 , further comprising:
 determining an orientation angle of the embedded color chart; and   fixing the orientation of the image based on the orientation angle.   
     
     
         5 . The computerized method of  claim 4 , wherein the determining the orientation angle comprises:
 performing edge detection on the image;   measuring an set of vector angles, wherein each angle in the set of vector angles is an angle of the gradient vector for each edge in the image;   creating an angle image from the set of vector angles;   creating a histogram from the angle image;   reducing the histogram to one spike; and   determining the orientation angle by selecting the maximum value in the reduced histogram.   
     
     
         6 . The computerized method of  claim 1 , further comprising:
 calibrating the image with the color profile.   
     
     
         7 . The computerized method of  claim 6 , further comprising:
 receiving a set of other images; and   calibrating the set of other images with the color profile.   
     
     
         8 . A computerized method comprising:
 locating automatically an embedded color chart in an image;   determining an orientation angle of the embedded color chart in the image; and   fixing the orientation of the image based on the orientation angle.   
     
     
         9 . The computerized method of  claim 8 , wherein the determining the orientation angle comprises:
 performing edge detection on the image;   measuring a set of vector angles, wherein each angle in the set of vector angles is an angle of the gradient vector for each edge in the image;   creating an angle image from the set of vector angles;   creating a histogram from the angle image;   reducing the histogram to one spike; and   determining the orientation angle by selecting the maximum value in the reduced histogram.   
     
     
         10 . The computerized method of  claim 9 , further comprising:
 calibrating the image with the color profile.   
     
     
         11 . The computerized method of  claim 10 , further comprising:
 receiving a set of other images; and   calibrating the set of other images with the color profile.   
     
     
         12 . A machine-readable medium having executable instructions to cause a processing system to perform a method comprising:
 receiving an image, wherein the image comprises an embedded color chart;   locating the embedded color chart without intervention of a user;   verifying the embedded color chart; and   creating a color profile for the image based on the embedded color chart.   
     
     
         13 . The machine-readable medium of  claim 12 , the method further comprising:
 computing an average horizontal scan line comprising a first set of pulses;   fitting a second set of generated pulses corresponding to a reference color chart to the first set of pulses;   determining if the first set of pulses matches the second set of generated pulses;   computing an average vertical scan line comprising a third set of pulses;   fitting a fourth set of generated pulses corresponding to a reference color chart to the third set of pulses; and   determining if the third set of pulses matches the second set of generated pulses; and   determining the location of the embedded color chart in the image based on the first and third set of pulses.   
     
     
         14 . The medium of  claim 12 , the method further comprising:
 determining an orientation angle of the embedded color chart; and   fixing the orientation of the image based on the orientation angle.   
     
     
         15 . The medium of  claim 14 , wherein the determining the orientation angle comprises:
 performing edge detection on the image;   measuring a set of vector angles, wherein each angle in the set of vector angles is an angle of the gradient vector for each edge in the image;   creating an angle image from the set of vector angles;   creating a histogram from the angle image;   reducing the histogram to one spike; and   determining the orientation angle by selecting the maximum value in the reduced histogram.   
     
     
         16 . The medium of  claim 14 , the method further comprising:
 calibrating the image with the color profile.   
     
     
         17 . The medium of  claim 16 , further comprising:
 receiving a set of other images; and   calibrating the set of other images with the color profile.   
     
     
         18 . A machine readable medium having executable instructions to cause a processing system to perform a method comprising:
 locating automatically an embedded color chart in an image;   determining an orientation angle of the embedded color chart in the image; and   fixing the orientation of the image based on the orientation angle.   
     
     
         19 . The medium of  claim 18 , wherein the determining the orientation angle comprises:
 performing edge detection on the image;   measuring a set of vector angles, wherein each angle in the set of vector angles is an angle of the gradient vector for each edge in the image;   creating an angle image from the set of vector angles;   creating a histogram from the angle image;   reducing the histogram to one spike; and   determining the orientation angle by selecting the maximum value in the reduced histogram.   
     
     
         20 . The medium of  claim 19 , the method further comprising:
 calibrating the image with the color profile.   
     
     
         21 . The medium of  claim 20 , the method further comprising:
 receiving a set of other images; and   calibrating the set of other images with the color profile.

Join the waitlist — get patent alerts

Track US2012076405A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.