Processing

Please wait...

Settings

Settings

Goto Application

1. US20170213102 - Method and apparatus for validity determination of a data dividing operation

Note: Text based on automatic Optical Character Recognition processes. Please use the PDF version for legal matters

[ EN ]

Claims

1. A method executed by a system comprising a hardware processor, comprising
in response to determining that a number of samples of operation data indicative of a range of validity of an operation to be performed by the system on image data exceeds a threshold, dividing the samples of operation data into a plurality of chunks, wherein a chunk of the plurality of chunks includes multiple samples of operation data;
determining respective partial convex hulls for respective chunks of the plurality of chunks;
determining a convex hull for the operation data based on a sum of the partial convex hulls that joins the partial convex hulls to produce the convex hull for the operation data;
determining whether the image data exceeds the range of validity of the operation data based on the convex hull for the operation data; and
modify the operation performed by the system on the image data in response to determining that the image data exceeds the range of validity of the operation data.
2. The method of claim 1, comprising determining the operation data by reducing a number of dimensions in initial operation data.
3. The method of claim 2, wherein the determining of the operation data comprises performing a principal component analysis (PCA) on the initial operation data.
4. The method of claim 2, comprising mapping the operation data to a model based on the reduced number of dimensions.
5. The method of claim 4, wherein the model is a linear model.
6. The method of claim 2, wherein reducing the number of dimensions in the initial operation data comprises iteratively reducing the number of dimensions in the initial operation data in response to determining that a number of samples in the operation data exceeds a threshold number.
7. The method of claim 1, comprising randomizing the operation data.
8. The method of claim 1, wherein at least some of the partial convex hulls are determined in parallel by respective processing units.
9. The method of claim 1, wherein the determining of whether the image data exceeds the range of validity of the operation data comprises mapping vertices of the convex hull to original dimensions of the operation data and comparing the image data against vertices in the original dimensions.
10. The method of claim 1, wherein modifying the operation performed by the system comprises modifying a printing operation.
11. The method of claim 1, wherein modifying the operation performed by the system comprises stopping the operation or changing a characteristic of the operation.
12. An apparatus comprising:
a processor; and
a non-transitory storage medium storing instructions executable on the processor to:
in response to determining that a number of samples of operation data indicative of a range of validity of an operation to be performed by a system on image data exceeds a threshold, divide the samples of operation data into a plurality of chunks;
determine partial convex hulls for respective chunks of the plurality of chunks;
determine a convex hull for the operation data based on joining the partial convex hulls by summing the partial convex hulls;
determine whether the image data exceeds the range of validity of the operation data based on the convex hull for the operation data; and
modify the operation of the system on the image data in response to determining that the image data exceeds the range of validity of the operation data.
13. The apparatus of claim 12, wherein the-instructions are executable on the processor to determine the operation data by reducing a number of dimensions in initial operation data.
14. The apparatus of claim 13, wherein the-instructions are executable on the processor to map the operation data to a model based on the reduced number of dimensions.
15. The apparatus of claim 12, comprising a plurality of processors to determine the partial convex hulls in parallel.
16. The apparatus of claim 12, wherein the apparatus is an image processing device, and the operation comprises an operation of the image processing device.
17. A non-transitory storage medium storing machine-readable instructions that upon execution cause a system to:
in response to determining that a number of samples of operation data indicative of a range of validity of an operation to be performed by the system on image data exceeds a threshold, divide the samples of operation data into a plurality of chunks;
determine partial convex hulls for respective chunks of the plurality of chunks;
determine a convex hull for the operation data based on joining the partial convex hulls by summing the partial convex hulls;
determine whether the image data exceeds the range of validity of the operation data based on the convex hull for the operation data; and
modify the operation of the system on the image data in response to determining that the image data exceeds the range of validity of the operation data.
18. The non-transitory storage medium of claim 17, wherein modifying the operation comprises modifying a printing operation.